mirror of
https://github.com/FlareSolverr/FlareSolverr.git
synced 2025-06-07 20:15:24 +00:00
Compare commits
118 Commits
Author | SHA1 | Date | |
---|---|---|---|
![]() |
3dd3e7559d | ||
![]() |
f21c1d51bc | ||
![]() |
957347f73a | ||
![]() |
c55080b0ec | ||
![]() |
639bfca020 | ||
![]() |
237694df76 | ||
![]() |
6e5d6f1795 | ||
![]() |
30804a86e5 | ||
![]() |
e0bdaf7745 | ||
![]() |
795365dbe4 | ||
![]() |
ce5369dd41 | ||
![]() |
600b09d498 | ||
![]() |
d1f19405a1 | ||
![]() |
82a1366d34 | ||
![]() |
a2fe9e7776 | ||
![]() |
6cc628df9e | ||
![]() |
8b1851eeb1 | ||
![]() |
54668a11e7 | ||
![]() |
701d8fb4ff | ||
![]() |
39a265ccb8 | ||
![]() |
e32b247014 | ||
![]() |
0d8fe8fe50 | ||
![]() |
718da3a36f | ||
![]() |
a798561338 | ||
![]() |
eb680efc90 | ||
![]() |
0f8f0bec25 | ||
![]() |
3d9bc5627b | ||
![]() |
dd7eaee2e3 | ||
![]() |
031177bbdb | ||
![]() |
a8644532a1 | ||
![]() |
e96161c873 | ||
![]() |
5a1f25cd52 | ||
![]() |
a2c0e4348e | ||
![]() |
2ecf88895b | ||
![]() |
984368edb5 | ||
![]() |
6c1d78cb84 | ||
![]() |
5a2c61601e | ||
![]() |
c304da2964 | ||
![]() |
b811412699 | ||
![]() |
0bb8de144f | ||
![]() |
38166dfaa0 | ||
![]() |
8dea0ed017 | ||
![]() |
20cd2944a7 | ||
![]() |
fd773e5909 | ||
![]() |
35c7bff3c8 | ||
![]() |
afdc1c7a8e | ||
![]() |
0bc7a4498c | ||
![]() |
c5a5f6d65e | ||
![]() |
aaf29be8e1 | ||
![]() |
800866d033 | ||
![]() |
043f18b231 | ||
![]() |
d21a332519 | ||
![]() |
3ca6d08f41 | ||
![]() |
227bd7ac72 | ||
![]() |
e6a08584c0 | ||
![]() |
df06d13cf8 | ||
![]() |
993b8c41ac | ||
![]() |
a4d42d7834 | ||
![]() |
1c855b8af0 | ||
![]() |
745c69491f | ||
![]() |
f7e316fd5a | ||
![]() |
16c8ab5f3d | ||
![]() |
7af311b73c | ||
![]() |
daec97532d | ||
![]() |
8d7ed48f21 | ||
![]() |
220f2599ae | ||
![]() |
d772cf3f50 | ||
![]() |
ab4365894b | ||
![]() |
3fa9631559 | ||
![]() |
04858c22fd | ||
![]() |
5085ca6990 | ||
![]() |
cd4df1e061 | ||
![]() |
6c79783f7c | ||
![]() |
4139e8d47c | ||
![]() |
1942eb5fdc | ||
![]() |
401bf5be76 | ||
![]() |
d8ffdd3061 | ||
![]() |
2d66590b08 | ||
![]() |
a217510dc7 | ||
![]() |
553bd8ab4f | ||
![]() |
1b197c3e53 | ||
![]() |
fd308f01be | ||
![]() |
b5eef32615 | ||
![]() |
644a843d89 | ||
![]() |
82e1c94c6f | ||
![]() |
fbc71516f5 | ||
![]() |
40bd1cba4c | ||
![]() |
d1588c1156 | ||
![]() |
b4ad583baa | ||
![]() |
5d31e551cc | ||
![]() |
d92845f34f | ||
![]() |
5d3b73ea9d | ||
![]() |
2aa095ed5d | ||
![]() |
687c8f75ae | ||
![]() |
22ed3d324b | ||
![]() |
5ba9ef03f3 | ||
![]() |
d2e144ea12 | ||
![]() |
313fb2c14b | ||
![]() |
6d69f40b58 | ||
![]() |
a1c36f60d2 | ||
![]() |
0edc50e271 | ||
![]() |
f4a4baa57c | ||
![]() |
f7e434c6e3 | ||
![]() |
7728f2ab31 | ||
![]() |
c920bea4ca | ||
![]() |
a785f83034 | ||
![]() |
b42c22f5b1 | ||
![]() |
9c62410a8b | ||
![]() |
b8768ae17d | ||
![]() |
9b2c602a1f | ||
![]() |
8316350b98 | ||
![]() |
33307ce461 | ||
![]() |
cedb7bc54e | ||
![]() |
6ecaf2362c | ||
![]() |
3c97c9603a | ||
![]() |
efaa5f31b6 | ||
![]() |
4db85a2d0f | ||
![]() |
66b9db21e5 |
14
.github/ISSUE_TEMPLATE/bug_report.yml
vendored
14
.github/ISSUE_TEMPLATE/bug_report.yml
vendored
@ -8,6 +8,13 @@ body:
|
||||
options:
|
||||
- label: I have checked the README
|
||||
required: true
|
||||
- type: checkboxes
|
||||
attributes:
|
||||
label: Have you followed our Troubleshooting?
|
||||
description: Please follow our <a href="https://github.com/FlareSolverr/FlareSolverr/wiki/Troubleshooting">Troubleshooting</a>.
|
||||
options:
|
||||
- label: I have followed your Troubleshooting
|
||||
required: true
|
||||
- type: checkboxes
|
||||
attributes:
|
||||
label: Is there already an issue for your problem?
|
||||
@ -22,6 +29,13 @@ body:
|
||||
options:
|
||||
- label: I have read the Discussions
|
||||
required: true
|
||||
- type: input
|
||||
attributes:
|
||||
label: Have you ACTUALLY checked all these?
|
||||
description: Please do not waste our time and yours; these checks are there for a reason, it is not just so you can tick boxes for fun. If you type <b>YES</b> and it is clear you did not or have put in no effort, your issue will be closed and locked without comment. If you type <b>NO</b> but still open this issue, you will be permanently blocked for timewasting.
|
||||
placeholder: YES or NO
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
attributes:
|
||||
label: Environment
|
||||
|
66
.github/workflows/release-docker.yml
vendored
66
.github/workflows/release-docker.yml
vendored
@ -4,50 +4,64 @@ on:
|
||||
push:
|
||||
tags:
|
||||
- 'v*.*.*'
|
||||
pull_request:
|
||||
branches:
|
||||
- master
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
build-docker-images:
|
||||
if: ${{ !github.event.pull_request.head.repo.fork }}
|
||||
runs-on: ubuntu-22.04
|
||||
steps:
|
||||
-
|
||||
name: Checkout
|
||||
uses: actions/checkout@v3
|
||||
-
|
||||
name: Downcase repo
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Downcase repo
|
||||
run: echo REPOSITORY=$(echo ${{ github.repository }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
|
||||
-
|
||||
name: Docker meta
|
||||
|
||||
- name: Docker meta
|
||||
id: docker_meta
|
||||
uses: crazy-max/ghaction-docker-meta@v3
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ env.REPOSITORY }},ghcr.io/${{ env.REPOSITORY }}
|
||||
tag-sha: false
|
||||
-
|
||||
name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v2
|
||||
-
|
||||
name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v2
|
||||
-
|
||||
name: Login to DockerHub
|
||||
uses: docker/login-action@v2
|
||||
images: |
|
||||
${{ env.REPOSITORY }},enable=${{ github.event_name != 'pull_request' }}
|
||||
ghcr.io/${{ env.REPOSITORY }}
|
||||
tags: |
|
||||
type=semver,pattern={{version}},prefix=v
|
||||
type=ref,event=pr
|
||||
flavor: |
|
||||
latest=auto
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v3
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Login to DockerHub
|
||||
uses: docker/login-action@v3
|
||||
if: github.event_name != 'pull_request'
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_TOKEN }}
|
||||
-
|
||||
name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v2
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.repository_owner }}
|
||||
password: ${{ secrets.GH_PAT }}
|
||||
-
|
||||
name: Build and push
|
||||
uses: docker/build-push-action@v3
|
||||
|
||||
- name: Build and push
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
file: ./Dockerfile
|
||||
platforms: linux/386,linux/amd64,linux/arm/v7,linux/arm64/v8
|
||||
push: ${{ github.event_name != 'pull_request' }}
|
||||
push: true
|
||||
tags: ${{ steps.docker_meta.outputs.tags }}
|
||||
labels: ${{ steps.docker_meta.outputs.labels }}
|
||||
|
4
.github/workflows/release.yml
vendored
4
.github/workflows/release.yml
vendored
@ -54,7 +54,7 @@ jobs:
|
||||
- name: Build artifacts
|
||||
run: |
|
||||
python -m pip install -r requirements.txt
|
||||
python -m pip install pyinstaller==5.9.0
|
||||
python -m pip install pyinstaller==5.13.0
|
||||
cd src
|
||||
python build_package.py
|
||||
|
||||
@ -83,7 +83,7 @@ jobs:
|
||||
- name: Build artifacts
|
||||
run: |
|
||||
python -m pip install -r requirements.txt
|
||||
python -m pip install pyinstaller==5.9.0
|
||||
python -m pip install pyinstaller==5.13.0
|
||||
cd src
|
||||
python build_package.py
|
||||
|
||||
|
3
.gitignore
vendored
3
.gitignore
vendored
@ -124,3 +124,6 @@ venv.bak/
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# node
|
||||
node_modules/
|
145
CHANGELOG.md
145
CHANGELOG.md
@ -1,5 +1,150 @@
|
||||
# Changelog
|
||||
|
||||
## v3.3.24 (2025/06/04)
|
||||
* Remove hidden character
|
||||
|
||||
## v3.3.23 (2025/06/04)
|
||||
* Update base image to bookworm. Thanks @rwjack
|
||||
|
||||
## v3.3.22 (2025/06/03)
|
||||
* Disable search engine choice screen
|
||||
* Fix headless=false stalling. Thanks @MAKMED1337
|
||||
* Change from click to keys. Thanks @sh4dowb
|
||||
* Don't open devtools
|
||||
* Bump Chromium to v137 for build
|
||||
* Bump requirements
|
||||
|
||||
## v3.3.21 (2024/06/26)
|
||||
* Add challenge selector to catch reloading page on non-English systems
|
||||
* Escape values for generated form used in request.post. Thanks @mynameisbogdan
|
||||
|
||||
## v3.3.20 (2024/06/21)
|
||||
* maxTimeout should always be int
|
||||
* Check not running in Docker before logging version_main error
|
||||
* Update Cloudflare challenge and checkbox selectors. Thanks @tenettow & @21hsmw
|
||||
|
||||
## v3.3.19 (2024/05/23)
|
||||
* Fix occasional headless issue on Linux when set to "false". Thanks @21hsmw
|
||||
|
||||
## v3.3.18 (2024/05/20)
|
||||
|
||||
* Fix LANG ENV for Linux
|
||||
* Fix Chrome v124+ not closing on Windows. Thanks @RileyXX
|
||||
|
||||
## v3.3.17 (2024/04/09)
|
||||
|
||||
* Fix file descriptor leak in service on quit(). Thanks @zkulis
|
||||
|
||||
## v3.3.16 (2024/02/28)
|
||||
|
||||
* Fix of the subprocess.STARTUPINFO() call. Thanks @ceconelo
|
||||
* Add FreeBSD support. Thanks @Asthowen
|
||||
* Use headless configuration properly. Thanks @hashworks
|
||||
|
||||
## v3.3.15 (2024/02/20)
|
||||
|
||||
* Fix looping challenges
|
||||
|
||||
## v3.3.14-hotfix2 (2024/02/17)
|
||||
|
||||
* Hotfix 2 - bad Chromium build, instances failed to terminate
|
||||
|
||||
## v3.3.14-hotfix (2024/02/17)
|
||||
|
||||
* Hotfix for Linux build - some Chrome files no longer exist
|
||||
|
||||
## v3.3.14 (2024/02/17)
|
||||
|
||||
* Update Chrome downloads. Thanks @opemvbs
|
||||
|
||||
## v3.3.13 (2024/01/07)
|
||||
|
||||
* Fix too many open files error
|
||||
|
||||
## v3.3.12 (2023/12/15)
|
||||
|
||||
* Fix looping challenges and invalid cookies
|
||||
|
||||
## v3.3.11 (2023/12/11)
|
||||
|
||||
* Update UC 3.5.4 & Selenium 4.15.2. Thanks @txtsd
|
||||
|
||||
## v3.3.10 (2023/11/14)
|
||||
|
||||
* Add LANG ENV - resolves issues with YGGtorrent
|
||||
|
||||
## v3.3.9 (2023/11/13)
|
||||
|
||||
* Fix for Docker build, capture TypeError
|
||||
|
||||
## v3.3.8 (2023/11/13)
|
||||
|
||||
* Fix headless=true for Chrome 117+. Thanks @NabiKAZ
|
||||
* Support running Chrome 119 from source. Thanks @koleg and @Chris7X
|
||||
* Fix "OSError: [WinError 6] The handle is invalid" on exit. Thanks @enesgorkemgenc
|
||||
|
||||
## v3.3.7 (2023/11/05)
|
||||
|
||||
* Bump to rebuild. Thanks @JoachimDorchies
|
||||
|
||||
## v3.3.6 (2023/09/15)
|
||||
|
||||
* Update checkbox selector, again
|
||||
|
||||
## v3.3.5 (2023/09/13)
|
||||
|
||||
* Change checkbox selector, support languages other than English
|
||||
|
||||
## v3.3.4 (2023/09/02)
|
||||
|
||||
* Update checkbox selector
|
||||
|
||||
## v3.3.3 (2023/08/31)
|
||||
|
||||
* Update undetected_chromedriver to v3.5.3
|
||||
|
||||
## v3.3.2 (2023/08/03)
|
||||
|
||||
* Fix URL domain in Prometheus exporter
|
||||
|
||||
## v3.3.1 (2023/08/03)
|
||||
|
||||
* Fix for Cloudflare verify checkbox
|
||||
* Fix HEADLESS=false in Windows binary
|
||||
* Fix Prometheus exporter for management and health endpoints
|
||||
* Remove misleading stack trace when the verify checkbox is not found
|
||||
* Revert "Update base Docker image to Debian Bookworm" #849
|
||||
* Revert "Install Chromium 115 from Debian testing" #849
|
||||
|
||||
## v3.3.0 (2023/08/02)
|
||||
|
||||
* Fix for new Cloudflare detection. Thanks @cedric-bour for #845
|
||||
* Add support for proxy authentication username/password. Thanks @jacobprice808 for #807
|
||||
* Implement Prometheus metrics
|
||||
* Fix Chromium Driver for Chrome / Chromium version > 114
|
||||
* Use Chromium 115 in binary packages (Windows and Linux)
|
||||
* Install Chromium 115 from Debian testing (Docker)
|
||||
* Update base Docker image to Debian Bookworm
|
||||
* Update Selenium 4.11.2
|
||||
* Update pyinstaller 5.13.0
|
||||
* Add more traces in build_package.py
|
||||
|
||||
## v3.2.2 (2023/07/16)
|
||||
|
||||
* Workaround for updated 'verify you are human' check
|
||||
|
||||
## v3.2.1 (2023/06/10)
|
||||
|
||||
* Kill dead Chrome processes in Windows
|
||||
* Fix Chrome GL erros in ASUSTOR NAS
|
||||
|
||||
## v3.2.0 (2023/05/23)
|
||||
|
||||
* Support "proxy" param in requests and sessions
|
||||
* Support "cookies" param in requests
|
||||
* Fix Chromium exec permissions in Linux package
|
||||
* Update Python dependencies
|
||||
|
||||
## v3.1.2 (2023/04/02)
|
||||
|
||||
* Fix headless mode in macOS
|
||||
|
15
Dockerfile
15
Dockerfile
@ -1,4 +1,4 @@
|
||||
FROM python:3.11-slim-bullseye as builder
|
||||
FROM python:3.11-slim-bookworm as builder
|
||||
|
||||
# Build dummy packages to skip installing them and their dependencies
|
||||
RUN apt-get update \
|
||||
@ -12,7 +12,7 @@ RUN apt-get update \
|
||||
&& equivs-build adwaita-icon-theme \
|
||||
&& mv adwaita-icon-theme_*.deb /adwaita-icon-theme.deb
|
||||
|
||||
FROM python:3.11-slim-bullseye
|
||||
FROM python:3.11-slim-bookworm
|
||||
|
||||
# Copy dummy packages
|
||||
COPY --from=builder /*.deb /
|
||||
@ -54,6 +54,7 @@ COPY src .
|
||||
COPY package.json ../
|
||||
|
||||
EXPOSE 8191
|
||||
EXPOSE 8192
|
||||
|
||||
# dumb-init avoids zombie chromium processes
|
||||
ENTRYPOINT ["/usr/bin/dumb-init", "--"]
|
||||
@ -61,17 +62,17 @@ ENTRYPOINT ["/usr/bin/dumb-init", "--"]
|
||||
CMD ["/usr/local/bin/python", "-u", "/app/flaresolverr.py"]
|
||||
|
||||
# Local build
|
||||
# docker build -t ngosang/flaresolverr:3.0.0 .
|
||||
# docker run -p 8191:8191 ngosang/flaresolverr:3.0.0
|
||||
# docker build -t ngosang/flaresolverr:3.3.24 .
|
||||
# docker run -p 8191:8191 ngosang/flaresolverr:3.3.24
|
||||
|
||||
# Multi-arch build
|
||||
# docker run --rm --privileged multiarch/qemu-user-static --reset -p yes
|
||||
# docker buildx create --use
|
||||
# docker buildx build -t ngosang/flaresolverr:3.0.0 --platform linux/386,linux/amd64,linux/arm/v7,linux/arm64/v8 .
|
||||
# docker buildx build -t ngosang/flaresolverr:3.3.24 --platform linux/386,linux/amd64,linux/arm/v7,linux/arm64/v8 .
|
||||
# add --push to publish in DockerHub
|
||||
|
||||
# Test multi-arch build
|
||||
# docker run --rm --privileged multiarch/qemu-user-static --reset -p yes
|
||||
# docker buildx create --use
|
||||
# docker buildx build -t ngosang/flaresolverr:3.0.0 --platform linux/arm/v7 --load .
|
||||
# docker run -p 8191:8191 --platform linux/arm/v7 ngosang/flaresolverr:3.0.0
|
||||
# docker buildx build -t ngosang/flaresolverr:3.3.24 --platform linux/arm/v7 --load .
|
||||
# docker run -p 8191:8191 --platform linux/arm/v7 ngosang/flaresolverr:3.3.24
|
||||
|
110
README.md
110
README.md
@ -45,7 +45,8 @@ Supported architectures are:
|
||||
| ARM32 | linux/arm/v7 |
|
||||
| ARM64 | linux/arm64 |
|
||||
|
||||
We provide a `docker-compose.yml` configuration file. Clone this repository and execute `docker-compose up -d` to start
|
||||
We provide a `docker-compose.yml` configuration file. Clone this repository and execute
|
||||
`docker-compose up -d` _(Compose V1)_ or `docker compose up -d` _(Compose V2)_ to start
|
||||
the container.
|
||||
|
||||
If you prefer the `docker cli` execute the following command.
|
||||
@ -78,28 +79,62 @@ This is the recommended way for Windows users.
|
||||
|
||||
* Install [Python 3.11](https://www.python.org/downloads/).
|
||||
* Install [Chrome](https://www.google.com/intl/en_us/chrome/) (all OS) or [Chromium](https://www.chromium.org/getting-involved/download-chromium/) (just Linux, it doesn't work in Windows) web browser.
|
||||
* (Only in Linux / macOS) Install [Xvfb](https://en.wikipedia.org/wiki/Xvfb) package.
|
||||
* (Only in Linux) Install [Xvfb](https://en.wikipedia.org/wiki/Xvfb) package.
|
||||
* (Only in macOS) Install [XQuartz](https://www.xquartz.org/) package.
|
||||
* Clone this repository and open a shell in that path.
|
||||
* Run `pip install -r requirements.txt` command to install FlareSolverr dependencies.
|
||||
* Run `python src/flaresolverr.py` command to start FlareSolverr.
|
||||
|
||||
### From source code (FreeBSD/TrueNAS CORE)
|
||||
|
||||
* Run `pkg install chromium python311 py311-pip xorg-vfbserver` command to install the required dependencies.
|
||||
* Clone this repository and open a shell in that path.
|
||||
* Run `python3.11 -m pip install -r requirements.txt` command to install FlareSolverr dependencies.
|
||||
* Run `python3.11 src/flaresolverr.py` command to start FlareSolverr.
|
||||
|
||||
### Systemd service
|
||||
|
||||
We provide an example Systemd unit file `flaresolverr.service` as reference. You have to modify the file to suit your needs: paths, user and environment variables.
|
||||
|
||||
## Usage
|
||||
|
||||
Example request:
|
||||
Example Bash request:
|
||||
```bash
|
||||
curl -L -X POST 'http://localhost:8191/v1' \
|
||||
-H 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
"cmd": "request.get",
|
||||
"url":"http://www.google.com/",
|
||||
"url": "http://www.google.com/",
|
||||
"maxTimeout": 60000
|
||||
}'
|
||||
```
|
||||
|
||||
Example Python request:
|
||||
```py
|
||||
import requests
|
||||
|
||||
url = "http://localhost:8191/v1"
|
||||
headers = {"Content-Type": "application/json"}
|
||||
data = {
|
||||
"cmd": "request.get",
|
||||
"url": "http://www.google.com/",
|
||||
"maxTimeout": 60000
|
||||
}
|
||||
response = requests.post(url, headers=headers, json=data)
|
||||
print(response.text)
|
||||
```
|
||||
|
||||
Example PowerShell request:
|
||||
```ps1
|
||||
$body = @{
|
||||
cmd = "request.get"
|
||||
url = "http://www.google.com/"
|
||||
maxTimeout = 60000
|
||||
} | ConvertTo-Json
|
||||
|
||||
irm -UseBasicParsing 'http://localhost:8191/v1' -Headers @{"Content-Type"="application/json"} -Method Post -Body $body
|
||||
```
|
||||
|
||||
### Commands
|
||||
|
||||
#### + `sessions.create`
|
||||
@ -110,10 +145,10 @@ cookies for the browser to use.
|
||||
|
||||
This also speeds up the requests since it won't have to launch a new browser instance for every request.
|
||||
|
||||
| Parameter | Notes |
|
||||
|-----------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| session | Optional. The session ID that you want to be assigned to the instance. If isn't set a random UUID will be assigned. |
|
||||
| proxy | Optional, default disabled. Eg: `"proxy": {"url": "http://127.0.0.1:8888"}`. You must include the proxy schema in the URL: `http://`, `socks4://` or `socks5://`. Authorization (username/password) is not supported. |
|
||||
| Parameter | Notes |
|
||||
|-----------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| session | Optional. The session ID that you want to be assigned to the instance. If isn't set a random UUID will be assigned. |
|
||||
| proxy | Optional, default disabled. Eg: `"proxy": {"url": "http://127.0.0.1:8888"}`. You must include the proxy schema in the URL: `http://`, `socks4://` or `socks5://`. Authorization (username/password) is supported. Eg: `"proxy": {"url": "http://127.0.0.1:8888", "username": "testuser", "password": "testpass"}` |
|
||||
|
||||
#### + `sessions.list`
|
||||
|
||||
@ -150,7 +185,7 @@ session. When you no longer need to use a session you should make sure to close
|
||||
| session | Optional. Will send the request from and existing browser instance. If one is not sent it will create a temporary instance that will be destroyed immediately after the request is completed. |
|
||||
| session_ttl_minutes | Optional. FlareSolverr will automatically rotate expired sessions based on the TTL provided in minutes. |
|
||||
| maxTimeout | Optional, default value 60000. Max timeout to solve the challenge in milliseconds. |
|
||||
| cookies | Optional. Will be used by the headless browser. Follow [this](https://github.com/puppeteer/puppeteer/blob/v3.3.0/docs/api.md#pagesetcookiecookies) format. |
|
||||
| cookies | Optional. Will be used by the headless browser. Eg: `"cookies": [{"name": "cookie1", "value": "value1"}, {"name": "cookie2", "value": "value2"}]`. |
|
||||
| returnOnlyCookies | Optional, default false. Only returns the cookies. Response data, headers and other parts of the response are removed. |
|
||||
| proxy | Optional, default disabled. Eg: `"proxy": {"url": "http://127.0.0.1:8888"}`. You must include the proxy schema in the URL: `http://`, `socks4://` or `socks5://`. Authorization (username/password) is not supported. (When the `session` parameter is set, the proxy is ignored; a session specific proxy can be set in `sessions.create`.) |
|
||||
|
||||
@ -226,22 +261,51 @@ This is the same as `request.get` but it takes one more param:
|
||||
|
||||
## Environment variables
|
||||
|
||||
| Name | Default | Notes |
|
||||
|-----------------|------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| LOG_LEVEL | info | Verbosity of the logging. Use `LOG_LEVEL=debug` for more information. |
|
||||
| LOG_HTML | false | Only for debugging. If `true` all HTML that passes through the proxy will be logged to the console in `debug` level. |
|
||||
| CAPTCHA_SOLVER | none | Captcha solving method. It is used when a captcha is encountered. See the Captcha Solvers section. |
|
||||
| TZ | UTC | Timezone used in the logs and the web browser. Example: `TZ=Europe/London`. |
|
||||
| HEADLESS | true | Only for debugging. To run the web browser in headless mode or visible. |
|
||||
| BROWSER_TIMEOUT | 40000 | If you are experiencing errors/timeouts because your system is slow, you can try to increase this value. Remember to increase the `maxTimeout` parameter too. |
|
||||
| TEST_URL | https://www.google.com | FlareSolverr makes a request on start to make sure the web browser is working. You can change that URL if it is blocked in your country. |
|
||||
| PORT | 8191 | Listening port. You don't need to change this if you are running on Docker. |
|
||||
| HOST | 0.0.0.0 | Listening interface. You don't need to change this if you are running on Docker. |
|
||||
| Name | Default | Notes |
|
||||
|--------------------|------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| LOG_LEVEL | info | Verbosity of the logging. Use `LOG_LEVEL=debug` for more information. |
|
||||
| LOG_HTML | false | Only for debugging. If `true` all HTML that passes through the proxy will be logged to the console in `debug` level. |
|
||||
| CAPTCHA_SOLVER | none | Captcha solving method. It is used when a captcha is encountered. See the Captcha Solvers section. |
|
||||
| TZ | UTC | Timezone used in the logs and the web browser. Example: `TZ=Europe/London`. |
|
||||
| LANG | none | Language used in the web browser. Example: `LANG=en_GB`. |
|
||||
| HEADLESS | true | Only for debugging. To run the web browser in headless mode or visible. |
|
||||
| BROWSER_TIMEOUT | 40000 | If you are experiencing errors/timeouts because your system is slow, you can try to increase this value. Remember to increase the `maxTimeout` parameter too. |
|
||||
| TEST_URL | https://www.google.com | FlareSolverr makes a request on start to make sure the web browser is working. You can change that URL if it is blocked in your country. |
|
||||
| PORT | 8191 | Listening port. You don't need to change this if you are running on Docker. |
|
||||
| HOST | 0.0.0.0 | Listening interface. You don't need to change this if you are running on Docker. |
|
||||
| PROMETHEUS_ENABLED | false | Enable Prometheus exporter. See the Prometheus section below. |
|
||||
| PROMETHEUS_PORT | 8192 | Listening port for Prometheus exporter. See the Prometheus section below. |
|
||||
|
||||
Environment variables are set differently depending on the operating system. Some examples:
|
||||
* Docker: Take a look at the Docker section in this document. Environment variables can be set in the `docker-compose.yml` file or in the Docker CLI command.
|
||||
* Linux: Run `export LOG_LEVEL=debug` and then start FlareSolverr in the same shell.
|
||||
* Windows: Open `cmd.exe`, run `set LOG_LEVEL=debug` and then start FlareSolverr in the same shell.
|
||||
* Linux: Run `export LOG_LEVEL=debug` and then run `flaresolverr` in the same shell.
|
||||
* Windows: Open `cmd.exe`, run `set LOG_LEVEL=debug` and then run `flaresolverr.exe` in the same shell.
|
||||
|
||||
## Prometheus exporter
|
||||
|
||||
The Prometheus exporter for FlareSolverr is disabled by default. It can be enabled with the environment variable `PROMETHEUS_ENABLED`. If you are using Docker make sure you expose the `PROMETHEUS_PORT`.
|
||||
|
||||
Example metrics:
|
||||
```shell
|
||||
# HELP flaresolverr_request_total Total requests with result
|
||||
# TYPE flaresolverr_request_total counter
|
||||
flaresolverr_request_total{domain="nowsecure.nl",result="solved"} 1.0
|
||||
# HELP flaresolverr_request_created Total requests with result
|
||||
# TYPE flaresolverr_request_created gauge
|
||||
flaresolverr_request_created{domain="nowsecure.nl",result="solved"} 1.690141657157109e+09
|
||||
# HELP flaresolverr_request_duration Request duration in seconds
|
||||
# TYPE flaresolverr_request_duration histogram
|
||||
flaresolverr_request_duration_bucket{domain="nowsecure.nl",le="0.0"} 0.0
|
||||
flaresolverr_request_duration_bucket{domain="nowsecure.nl",le="10.0"} 1.0
|
||||
flaresolverr_request_duration_bucket{domain="nowsecure.nl",le="25.0"} 1.0
|
||||
flaresolverr_request_duration_bucket{domain="nowsecure.nl",le="50.0"} 1.0
|
||||
flaresolverr_request_duration_bucket{domain="nowsecure.nl",le="+Inf"} 1.0
|
||||
flaresolverr_request_duration_count{domain="nowsecure.nl"} 1.0
|
||||
flaresolverr_request_duration_sum{domain="nowsecure.nl"} 5.858
|
||||
# HELP flaresolverr_request_duration_created Request duration in seconds
|
||||
# TYPE flaresolverr_request_duration_created gauge
|
||||
flaresolverr_request_duration_created{domain="nowsecure.nl"} 1.6901416571570296e+09
|
||||
```
|
||||
|
||||
## Captcha Solvers
|
||||
|
||||
@ -253,7 +317,7 @@ solve a captcha.
|
||||
If this is the case, FlareSolverr will return the error `Captcha detected but no automatic solver is configured.`
|
||||
|
||||
FlareSolverr can be customized to solve the CAPTCHA automatically by setting the environment variable `CAPTCHA_SOLVER`
|
||||
to the file name of one of the adapters inside the [/captcha](src/captcha) directory.
|
||||
to the file name of one of the adapters inside the `/captcha` directory.
|
||||
|
||||
## Related projects
|
||||
|
||||
|
19
flaresolverr.service
Normal file
19
flaresolverr.service
Normal file
@ -0,0 +1,19 @@
|
||||
[Unit]
|
||||
Description=FlareSolverr
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
SyslogIdentifier=flaresolverr
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
Type=simple
|
||||
User=flaresolverr
|
||||
Group=flaresolverr
|
||||
Environment="LOG_LEVEL=info"
|
||||
Environment="CAPTCHA_SOLVER=none"
|
||||
WorkingDirectory=/opt/flaresolverr
|
||||
ExecStart=/opt/flaresolverr/flaresolverr
|
||||
TimeoutStopSec=30
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "flaresolverr",
|
||||
"version": "3.1.2",
|
||||
"version": "3.3.24",
|
||||
"description": "Proxy server to bypass Cloudflare protection",
|
||||
"author": "Diego Heras (ngosang / ngosang@hotmail.es)",
|
||||
"license": "MIT"
|
||||
|
@ -1,12 +1,13 @@
|
||||
bottle==0.12.25
|
||||
waitress==2.1.2
|
||||
selenium==4.8.3
|
||||
waitress==3.0.1
|
||||
selenium==4.15.2
|
||||
func-timeout==4.3.5
|
||||
prometheus-client==0.17.1
|
||||
# required by undetected_chromedriver
|
||||
requests==2.28.2
|
||||
certifi==2022.12.7
|
||||
websockets==10.4
|
||||
# only required for linux
|
||||
xvfbwrapper==0.2.9
|
||||
requests==2.32.3
|
||||
certifi==2024.07.04
|
||||
websockets==11.0.3
|
||||
# only required for linux and macos
|
||||
xvfbwrapper==0.2.9; platform_system != "Windows"
|
||||
# only required for windows
|
||||
pefile==2023.2.7
|
||||
pefile==2023.2.7; platform_system == "Windows"
|
||||
|
66
src/bottle_plugins/prometheus_plugin.py
Normal file
66
src/bottle_plugins/prometheus_plugin.py
Normal file
@ -0,0 +1,66 @@
|
||||
import logging
|
||||
import os
|
||||
import urllib.parse
|
||||
|
||||
from bottle import request
|
||||
from dtos import V1RequestBase, V1ResponseBase
|
||||
from metrics import start_metrics_http_server, REQUEST_COUNTER, REQUEST_DURATION
|
||||
|
||||
PROMETHEUS_ENABLED = os.environ.get('PROMETHEUS_ENABLED', 'false').lower() == 'true'
|
||||
PROMETHEUS_PORT = int(os.environ.get('PROMETHEUS_PORT', 8192))
|
||||
|
||||
|
||||
def setup():
|
||||
if PROMETHEUS_ENABLED:
|
||||
start_metrics_http_server(PROMETHEUS_PORT)
|
||||
|
||||
|
||||
def prometheus_plugin(callback):
|
||||
"""
|
||||
Bottle plugin to expose Prometheus metrics
|
||||
http://bottlepy.org/docs/dev/plugindev.html
|
||||
"""
|
||||
def wrapper(*args, **kwargs):
|
||||
actual_response = callback(*args, **kwargs)
|
||||
|
||||
if PROMETHEUS_ENABLED:
|
||||
try:
|
||||
export_metrics(actual_response)
|
||||
except Exception as e:
|
||||
logging.warning("Error exporting metrics: " + str(e))
|
||||
|
||||
return actual_response
|
||||
|
||||
def export_metrics(actual_response):
|
||||
res = V1ResponseBase(actual_response)
|
||||
|
||||
if res.startTimestamp is None or res.endTimestamp is None:
|
||||
# skip management and healthcheck endpoints
|
||||
return
|
||||
|
||||
domain = "unknown"
|
||||
if res.solution and res.solution.url:
|
||||
domain = parse_domain_url(res.solution.url)
|
||||
else:
|
||||
# timeout error
|
||||
req = V1RequestBase(request.json)
|
||||
if req.url:
|
||||
domain = parse_domain_url(req.url)
|
||||
|
||||
run_time = (res.endTimestamp - res.startTimestamp) / 1000
|
||||
REQUEST_DURATION.labels(domain=domain).observe(run_time)
|
||||
|
||||
result = "unknown"
|
||||
if res.message == "Challenge solved!":
|
||||
result = "solved"
|
||||
elif res.message == "Challenge not detected!":
|
||||
result = "not_detected"
|
||||
elif res.message.startswith("Error"):
|
||||
result = "error"
|
||||
REQUEST_COUNTER.labels(domain=domain, result=result).inc()
|
||||
|
||||
def parse_domain_url(url):
|
||||
parsed_url = urllib.parse.urlparse(url)
|
||||
return parsed_url.hostname
|
||||
|
||||
return wrapper
|
@ -25,8 +25,8 @@ def clean_files():
|
||||
|
||||
def download_chromium():
|
||||
# https://commondatastorage.googleapis.com/chromium-browser-snapshots/index.html?prefix=Linux_x64/
|
||||
revision = "1090006" if os.name == 'nt' else '1090007'
|
||||
arch = 'Win' if os.name == 'nt' else 'Linux_x64'
|
||||
revision = "1453032" if os.name == 'nt' else '1453031'
|
||||
arch = 'Win_x64' if os.name == 'nt' else 'Linux_x64'
|
||||
dl_file = 'chrome-win' if os.name == 'nt' else 'chrome-linux'
|
||||
dl_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), os.pardir, 'dist_chrome')
|
||||
dl_path_folder = os.path.join(dl_path, dl_file)
|
||||
@ -50,17 +50,32 @@ def download_chromium():
|
||||
with zipfile.ZipFile(dl_path_zip, 'r') as zip_ref:
|
||||
zip_ref.extractall(dl_path)
|
||||
os.remove(dl_path_zip)
|
||||
shutil.move(dl_path_folder, os.path.join(dl_path, "chrome"))
|
||||
|
||||
chrome_path = os.path.join(dl_path, "chrome")
|
||||
shutil.move(dl_path_folder, chrome_path)
|
||||
print("Extracted in: " + chrome_path)
|
||||
|
||||
if os.name != 'nt':
|
||||
# Give executable permissions for *nix
|
||||
# file * | grep executable | cut -d: -f1
|
||||
print("Giving executable permissions...")
|
||||
execs = ['chrome', 'chrome_crashpad_handler', 'chrome_sandbox', 'chrome-wrapper', 'xdg-mime', 'xdg-settings']
|
||||
for exec_file in execs:
|
||||
exec_path = os.path.join(chrome_path, exec_file)
|
||||
os.chmod(exec_path, 0o755)
|
||||
|
||||
|
||||
def run_pyinstaller():
|
||||
sep = ';' if os.name == 'nt' else ':'
|
||||
subprocess.check_call([sys.executable, "-m", "PyInstaller",
|
||||
"--icon", "resources/flaresolverr_logo.ico",
|
||||
"--add-data", f"package.json{sep}.",
|
||||
"--add-data", f"{os.path.join('dist_chrome', 'chrome')}{sep}chrome",
|
||||
os.path.join("src", "flaresolverr.py")],
|
||||
cwd=os.pardir)
|
||||
result = subprocess.run([sys.executable, "-m", "PyInstaller",
|
||||
"--icon", "resources/flaresolverr_logo.ico",
|
||||
"--add-data", f"package.json{sep}.",
|
||||
"--add-data", f"{os.path.join('dist_chrome', 'chrome')}{sep}chrome",
|
||||
os.path.join("src", "flaresolverr.py")],
|
||||
cwd=os.pardir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
if result.returncode != 0:
|
||||
print(result.stderr.decode('utf-8'))
|
||||
raise Exception("Error running pyInstaller")
|
||||
|
||||
|
||||
def compress_package():
|
||||
|
@ -8,6 +8,7 @@ from bottle import run, response, Bottle, request, ServerAdapter
|
||||
|
||||
from bottle_plugins.error_plugin import error_plugin
|
||||
from bottle_plugins.logger_plugin import logger_plugin
|
||||
from bottle_plugins import prometheus_plugin
|
||||
from dtos import V1RequestBase
|
||||
import flaresolverr_service
|
||||
import utils
|
||||
@ -24,10 +25,6 @@ class JSONErrorBottle(Bottle):
|
||||
|
||||
app = JSONErrorBottle()
|
||||
|
||||
# plugin order is important
|
||||
app.install(logger_plugin)
|
||||
app.install(error_plugin)
|
||||
|
||||
|
||||
@app.route('/')
|
||||
def index():
|
||||
@ -65,6 +62,12 @@ if __name__ == "__main__":
|
||||
if sys.version_info < (3, 9):
|
||||
raise Exception("The Python version is less than 3.9, a version equal to or higher is required.")
|
||||
|
||||
# fix for HEADLESS=false in Windows binary
|
||||
# https://stackoverflow.com/a/27694505
|
||||
if os.name == 'nt':
|
||||
import multiprocessing
|
||||
multiprocessing.freeze_support()
|
||||
|
||||
# fix ssl certificates for compiled binaries
|
||||
# https://github.com/pyinstaller/pyinstaller/issues/7229
|
||||
# https://stackoverflow.com/questions/55736855/how-to-change-the-cafile-argument-in-the-ssl-module-in-python3
|
||||
@ -98,9 +101,19 @@ if __name__ == "__main__":
|
||||
logging.info(f'FlareSolverr {utils.get_flaresolverr_version()}')
|
||||
logging.debug('Debug log enabled')
|
||||
|
||||
# Get current OS for global variable
|
||||
utils.get_current_platform()
|
||||
|
||||
# test browser installation
|
||||
flaresolverr_service.test_browser_installation()
|
||||
|
||||
# start bootle plugins
|
||||
# plugin order is important
|
||||
app.install(logger_plugin)
|
||||
app.install(error_plugin)
|
||||
prometheus_plugin.setup()
|
||||
app.install(prometheus_plugin.prometheus_plugin)
|
||||
|
||||
# start webserver
|
||||
# default server 'wsgiref' does not support concurrent requests
|
||||
# https://github.com/FlareSolverr/FlareSolverr/issues/680
|
||||
|
@ -3,12 +3,14 @@ import platform
|
||||
import sys
|
||||
import time
|
||||
from datetime import timedelta
|
||||
from urllib.parse import unquote
|
||||
from html import escape
|
||||
from urllib.parse import unquote, quote
|
||||
|
||||
from func_timeout import FunctionTimedOut, func_timeout
|
||||
from selenium.common import TimeoutException
|
||||
from selenium.webdriver.chrome.webdriver import WebDriver
|
||||
from selenium.webdriver.common.by import By
|
||||
from selenium.webdriver.common.keys import Keys
|
||||
from selenium.webdriver.support.expected_conditions import (
|
||||
presence_of_element_located, staleness_of, title_is)
|
||||
from selenium.webdriver.common.action_chains import ActionChains
|
||||
@ -40,13 +42,13 @@ CHALLENGE_TITLES = [
|
||||
]
|
||||
CHALLENGE_SELECTORS = [
|
||||
# Cloudflare
|
||||
'#cf-challenge-running', '.ray_id', '.attack-box', '#cf-please-wait', '#challenge-spinner', '#trk_jschal_js',
|
||||
'#cf-challenge-running', '.ray_id', '.attack-box', '#cf-please-wait', '#challenge-spinner', '#trk_jschal_js', '#turnstile-wrapper', '.lds-ring',
|
||||
# Custom CloudFlare for EbookParadijs, Film-Paleis, MuziekFabriek and Puur-Hollands
|
||||
'td.info #js_info',
|
||||
# Fairlane / pararius.com
|
||||
'div.vc div.text-box h2'
|
||||
]
|
||||
SHORT_TIMEOUT = 10
|
||||
SHORT_TIMEOUT = 1
|
||||
SESSIONS_STORAGE = SessionsStorage()
|
||||
|
||||
|
||||
@ -119,7 +121,7 @@ def _controller_v1_handler(req: V1RequestBase) -> V1ResponseBase:
|
||||
logging.warning("Request parameter 'userAgent' was removed in FlareSolverr v2.")
|
||||
|
||||
# set default values
|
||||
if req.maxTimeout is None or req.maxTimeout < 1:
|
||||
if req.maxTimeout is None or int(req.maxTimeout) < 1:
|
||||
req.maxTimeout = 60000
|
||||
|
||||
# execute the command
|
||||
@ -179,7 +181,7 @@ def _cmd_request_post(req: V1RequestBase) -> V1ResponseBase:
|
||||
def _cmd_sessions_create(req: V1RequestBase) -> V1ResponseBase:
|
||||
logging.debug("Creating new session...")
|
||||
|
||||
session, fresh = SESSIONS_STORAGE.create(session_id=req.session)
|
||||
session, fresh = SESSIONS_STORAGE.create(session_id=req.session, proxy=req.proxy)
|
||||
session_id = session.session_id
|
||||
|
||||
if not fresh:
|
||||
@ -220,7 +222,7 @@ def _cmd_sessions_destroy(req: V1RequestBase) -> V1ResponseBase:
|
||||
|
||||
|
||||
def _resolve_challenge(req: V1RequestBase, method: str) -> ChallengeResolutionT:
|
||||
timeout = req.maxTimeout / 1000
|
||||
timeout = int(req.maxTimeout) / 1000
|
||||
driver = None
|
||||
try:
|
||||
if req.session:
|
||||
@ -236,41 +238,34 @@ def _resolve_challenge(req: V1RequestBase, method: str) -> ChallengeResolutionT:
|
||||
|
||||
driver = session.driver
|
||||
else:
|
||||
driver = utils.get_webdriver()
|
||||
driver = utils.get_webdriver(req.proxy)
|
||||
logging.debug('New instance of webdriver has been created to perform the request')
|
||||
return func_timeout(timeout, _evil_logic, (req, driver, method))
|
||||
except FunctionTimedOut:
|
||||
raise Exception(f'Error solving the challenge. Timeout after {timeout} seconds.')
|
||||
except Exception as e:
|
||||
raise Exception('Error solving the challenge. ' + str(e))
|
||||
raise Exception('Error solving the challenge. ' + str(e).replace('\n', '\\n'))
|
||||
finally:
|
||||
if not req.session and driver is not None:
|
||||
if utils.PLATFORM_VERSION == "nt":
|
||||
driver.close()
|
||||
driver.quit()
|
||||
logging.debug('A used instance of webdriver has been destroyed')
|
||||
|
||||
|
||||
def click_verify(driver: WebDriver):
|
||||
try:
|
||||
logging.debug("Try to find the Cloudflare verify checkbox")
|
||||
iframe = driver.find_element(By.XPATH, "//iframe[@title='Widget containing a Cloudflare security challenge']")
|
||||
driver.switch_to.frame(iframe)
|
||||
checkbox = driver.find_element(
|
||||
by=By.XPATH,
|
||||
value='//*[@id="cf-stage"]//label[@class="ctp-checkbox-label"]/input',
|
||||
)
|
||||
if checkbox:
|
||||
actions = ActionChains(driver)
|
||||
actions.move_to_element_with_offset(checkbox, 5, 7)
|
||||
actions.click(checkbox)
|
||||
actions.perform()
|
||||
logging.debug("Cloudflare verify checkbox found and clicked")
|
||||
logging.debug("Try to find the Cloudflare verify checkbox...")
|
||||
actions = ActionChains(driver)
|
||||
actions.pause(5).send_keys(Keys.TAB).pause(1).send_keys(Keys.SPACE).perform()
|
||||
logging.debug("Cloudflare verify checkbox found and clicked!")
|
||||
except Exception:
|
||||
logging.debug("Cloudflare verify checkbox not found on the page")
|
||||
logging.debug("Cloudflare verify checkbox not found on the page.")
|
||||
finally:
|
||||
driver.switch_to.default_content()
|
||||
|
||||
try:
|
||||
logging.debug("Try to find the Cloudflare 'Verify you are human' button")
|
||||
logging.debug("Try to find the Cloudflare 'Verify you are human' button...")
|
||||
button = driver.find_element(
|
||||
by=By.XPATH,
|
||||
value="//input[@type='button' and @value='Verify you are human']",
|
||||
@ -280,10 +275,9 @@ def click_verify(driver: WebDriver):
|
||||
actions.move_to_element_with_offset(button, 5, 7)
|
||||
actions.click(button)
|
||||
actions.perform()
|
||||
logging.debug("The Cloudflare 'Verify you are human' button found and clicked")
|
||||
except Exception as e:
|
||||
logging.debug("The Cloudflare 'Verify you are human' button not found on the page")
|
||||
# print(e)
|
||||
logging.debug("The Cloudflare 'Verify you are human' button found and clicked!")
|
||||
except Exception:
|
||||
logging.debug("The Cloudflare 'Verify you are human' button not found on the page.")
|
||||
|
||||
time.sleep(2)
|
||||
|
||||
@ -293,16 +287,29 @@ def _evil_logic(req: V1RequestBase, driver: WebDriver, method: str) -> Challenge
|
||||
res.status = STATUS_OK
|
||||
res.message = ""
|
||||
|
||||
|
||||
# navigate to the page
|
||||
logging.debug(f'Navigating to... {req.url}')
|
||||
if method == 'POST':
|
||||
_post_request(req, driver)
|
||||
else:
|
||||
driver.get(req.url)
|
||||
if utils.get_config_log_html():
|
||||
logging.debug(f"Response HTML:\n{driver.page_source}")
|
||||
|
||||
# set cookies if required
|
||||
if req.cookies is not None and len(req.cookies) > 0:
|
||||
logging.debug(f'Setting cookies...')
|
||||
for cookie in req.cookies:
|
||||
driver.delete_cookie(cookie['name'])
|
||||
driver.add_cookie(cookie)
|
||||
# reload the page
|
||||
if method == 'POST':
|
||||
_post_request(req, driver)
|
||||
else:
|
||||
driver.get(req.url)
|
||||
|
||||
# wait for the page
|
||||
if utils.get_config_log_html():
|
||||
logging.debug(f"Response HTML:\n{driver.page_source}")
|
||||
html_element = driver.find_element(By.TAG_NAME, "html")
|
||||
page_title = driver.title
|
||||
|
||||
@ -407,7 +414,7 @@ def _post_request(req: V1RequestBase, driver: WebDriver):
|
||||
value = unquote(parts[1])
|
||||
except Exception:
|
||||
value = parts[1]
|
||||
post_form += f'<input type="text" name="{name}" value="{value}"><br>'
|
||||
post_form += f'<input type="text" name="{escape(quote(name))}" value="{escape(quote(value))}"><br>'
|
||||
post_form += '</form>'
|
||||
html_content = f"""
|
||||
<!DOCTYPE html>
|
||||
@ -417,4 +424,4 @@ def _post_request(req: V1RequestBase, driver: WebDriver):
|
||||
<script>document.getElementById('hackForm').submit();</script>
|
||||
</body>
|
||||
</html>"""
|
||||
driver.get("data:text/html;charset=utf-8," + html_content)
|
||||
driver.get("data:text/html;charset=utf-8,{html_content}".format(html_content=html_content))
|
||||
|
32
src/metrics.py
Normal file
32
src/metrics.py
Normal file
@ -0,0 +1,32 @@
|
||||
import logging
|
||||
|
||||
from prometheus_client import Counter, Histogram, start_http_server
|
||||
import time
|
||||
|
||||
REQUEST_COUNTER = Counter(
|
||||
name='flaresolverr_request',
|
||||
documentation='Total requests with result',
|
||||
labelnames=['domain', 'result']
|
||||
)
|
||||
REQUEST_DURATION = Histogram(
|
||||
name='flaresolverr_request_duration',
|
||||
documentation='Request duration in seconds',
|
||||
labelnames=['domain'],
|
||||
buckets=[0, 10, 25, 50]
|
||||
)
|
||||
|
||||
|
||||
def serve(port):
|
||||
start_http_server(port=port)
|
||||
while True:
|
||||
time.sleep(600)
|
||||
|
||||
|
||||
def start_metrics_http_server(prometheus_port: int):
|
||||
logging.info(f"Serving Prometheus exporter on http://0.0.0.0:{prometheus_port}/metrics")
|
||||
from threading import Thread
|
||||
Thread(
|
||||
target=serve,
|
||||
kwargs=dict(port=prometheus_port),
|
||||
daemon=True,
|
||||
).start()
|
@ -25,7 +25,8 @@ class SessionsStorage:
|
||||
def __init__(self):
|
||||
self.sessions = {}
|
||||
|
||||
def create(self, session_id: Optional[str] = None, force_new: Optional[bool] = False) -> Tuple[Session, bool]:
|
||||
def create(self, session_id: Optional[str] = None, proxy: Optional[dict] = None,
|
||||
force_new: Optional[bool] = False) -> Tuple[Session, bool]:
|
||||
"""create creates new instance of WebDriver if necessary,
|
||||
assign defined (or newly generated) session_id to the instance
|
||||
and returns the session object. If a new session has been created
|
||||
@ -44,7 +45,7 @@ class SessionsStorage:
|
||||
if self.exists(session_id):
|
||||
return self.sessions[session_id], False
|
||||
|
||||
driver = utils.get_webdriver()
|
||||
driver = utils.get_webdriver(proxy)
|
||||
created_at = datetime.now()
|
||||
session = Session(session_id, driver, created_at)
|
||||
|
||||
@ -65,6 +66,8 @@ class SessionsStorage:
|
||||
return False
|
||||
|
||||
session = self.sessions.pop(session_id)
|
||||
if utils.PLATFORM_VERSION == "nt":
|
||||
session.driver.close()
|
||||
session.driver.quit()
|
||||
return True
|
||||
|
||||
|
181
src/tests.py
181
src/tests.py
@ -1,4 +1,5 @@
|
||||
import unittest
|
||||
from typing import Optional
|
||||
|
||||
from webtest import TestApp
|
||||
|
||||
@ -7,7 +8,7 @@ import flaresolverr
|
||||
import utils
|
||||
|
||||
|
||||
def _find_obj_by_key(key: str, value: str, _list: list) -> dict | None:
|
||||
def _find_obj_by_key(key: str, value: str, _list: list) -> Optional[dict]:
|
||||
for obj in _list:
|
||||
if obj[key] == value:
|
||||
return obj
|
||||
@ -28,6 +29,8 @@ class TestFlareSolverr(unittest.TestCase):
|
||||
cloudflare_blocked_url = "https://cpasbiens3.fr/index.php?do=search&subaction=search"
|
||||
|
||||
app = TestApp(flaresolverr.app)
|
||||
# wait until the server is ready
|
||||
app.get('/')
|
||||
|
||||
def test_wrong_endpoint(self):
|
||||
res = self.app.get('/wrong', status=404)
|
||||
@ -236,7 +239,45 @@ class TestFlareSolverr(unittest.TestCase):
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
# todo: test Cmd 'request.get' should return OK with 'cookies' param
|
||||
def test_v1_endpoint_request_get_cookies_param(self):
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "request.get",
|
||||
"url": self.google_url,
|
||||
"cookies": [
|
||||
{
|
||||
"name": "testcookie1",
|
||||
"value": "testvalue1"
|
||||
},
|
||||
{
|
||||
"name": "testcookie2",
|
||||
"value": "testvalue2"
|
||||
}
|
||||
]
|
||||
})
|
||||
self.assertEqual(res.status_code, 200)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_OK, body.status)
|
||||
self.assertEqual("Challenge not detected!", body.message)
|
||||
self.assertGreater(body.startTimestamp, 10000)
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
solution = body.solution
|
||||
self.assertIn(self.google_url, solution.url)
|
||||
self.assertEqual(solution.status, 200)
|
||||
self.assertIs(len(solution.headers), 0)
|
||||
self.assertIn("<title>Google</title>", solution.response)
|
||||
self.assertGreater(len(solution.cookies), 1)
|
||||
self.assertIn("Chrome/", solution.userAgent)
|
||||
|
||||
user_cookie1 = _find_obj_by_key("name", "testcookie1", solution.cookies)
|
||||
self.assertIsNotNone(user_cookie1, "User cookie 1 not found")
|
||||
self.assertEqual("testvalue1", user_cookie1["value"])
|
||||
|
||||
user_cookie2 = _find_obj_by_key("name", "testcookie2", solution.cookies)
|
||||
self.assertIsNotNone(user_cookie2, "User cookie 2 not found")
|
||||
self.assertEqual("testvalue2", user_cookie2["value"])
|
||||
|
||||
def test_v1_endpoint_request_get_returnOnlyCookies_param(self):
|
||||
res = self.app.post_json('/v1', {
|
||||
@ -261,10 +302,124 @@ class TestFlareSolverr(unittest.TestCase):
|
||||
self.assertGreater(len(solution.cookies), 0)
|
||||
self.assertIn("Chrome/", solution.userAgent)
|
||||
|
||||
# todo: test Cmd 'request.get' should return OK with HTTP 'proxy' param
|
||||
# todo: test Cmd 'request.get' should return OK with HTTP 'proxy' param with credentials
|
||||
# todo: test Cmd 'request.get' should return OK with SOCKSv5 'proxy' param
|
||||
# todo: test Cmd 'request.get' should fail with wrong 'proxy' param
|
||||
def test_v1_endpoint_request_get_proxy_http_param(self):
|
||||
"""
|
||||
To configure TinyProxy in local:
|
||||
* sudo vim /etc/tinyproxy/tinyproxy.conf
|
||||
* edit => LogFile "/tmp/tinyproxy.log"
|
||||
* edit => Syslog Off
|
||||
* sudo tinyproxy -d
|
||||
* sudo tail -f /tmp/tinyproxy.log
|
||||
"""
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "request.get",
|
||||
"url": self.google_url,
|
||||
"proxy": {
|
||||
"url": self.proxy_url
|
||||
}
|
||||
})
|
||||
self.assertEqual(res.status_code, 200)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_OK, body.status)
|
||||
self.assertEqual("Challenge not detected!", body.message)
|
||||
self.assertGreater(body.startTimestamp, 10000)
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
solution = body.solution
|
||||
self.assertIn(self.google_url, solution.url)
|
||||
self.assertEqual(solution.status, 200)
|
||||
self.assertIs(len(solution.headers), 0)
|
||||
self.assertIn("<title>Google</title>", solution.response)
|
||||
self.assertGreater(len(solution.cookies), 0)
|
||||
self.assertIn("Chrome/", solution.userAgent)
|
||||
|
||||
def test_v1_endpoint_request_get_proxy_http_param_with_credentials(self):
|
||||
"""
|
||||
To configure TinyProxy in local:
|
||||
* sudo vim /etc/tinyproxy/tinyproxy.conf
|
||||
* edit => LogFile "/tmp/tinyproxy.log"
|
||||
* edit => Syslog Off
|
||||
* add => BasicAuth testuser testpass
|
||||
* sudo tinyproxy -d
|
||||
* sudo tail -f /tmp/tinyproxy.log
|
||||
"""
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "request.get",
|
||||
"url": self.google_url,
|
||||
"proxy": {
|
||||
"url": self.proxy_url,
|
||||
"username": "testuser",
|
||||
"password": "testpass"
|
||||
}
|
||||
})
|
||||
self.assertEqual(res.status_code, 200)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_OK, body.status)
|
||||
self.assertEqual("Challenge not detected!", body.message)
|
||||
self.assertGreater(body.startTimestamp, 10000)
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
solution = body.solution
|
||||
self.assertIn(self.google_url, solution.url)
|
||||
self.assertEqual(solution.status, 200)
|
||||
self.assertIs(len(solution.headers), 0)
|
||||
self.assertIn("<title>Google</title>", solution.response)
|
||||
self.assertGreater(len(solution.cookies), 0)
|
||||
self.assertIn("Chrome/", solution.userAgent)
|
||||
|
||||
def test_v1_endpoint_request_get_proxy_socks_param(self):
|
||||
"""
|
||||
To configure Dante in local:
|
||||
* https://linuxhint.com/set-up-a-socks5-proxy-on-ubuntu-with-dante/
|
||||
* sudo vim /etc/sockd.conf
|
||||
* sudo systemctl restart sockd.service
|
||||
* curl --socks5 socks5://127.0.0.1:1080 https://www.google.com
|
||||
"""
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "request.get",
|
||||
"url": self.google_url,
|
||||
"proxy": {
|
||||
"url": self.proxy_socks_url
|
||||
}
|
||||
})
|
||||
self.assertEqual(res.status_code, 200)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_OK, body.status)
|
||||
self.assertEqual("Challenge not detected!", body.message)
|
||||
self.assertGreater(body.startTimestamp, 10000)
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
solution = body.solution
|
||||
self.assertIn(self.google_url, solution.url)
|
||||
self.assertEqual(solution.status, 200)
|
||||
self.assertIs(len(solution.headers), 0)
|
||||
self.assertIn("<title>Google</title>", solution.response)
|
||||
self.assertGreater(len(solution.cookies), 0)
|
||||
self.assertIn("Chrome/", solution.userAgent)
|
||||
|
||||
def test_v1_endpoint_request_get_proxy_wrong_param(self):
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "request.get",
|
||||
"url": self.google_url,
|
||||
"proxy": {
|
||||
"url": "http://127.0.0.1:43210"
|
||||
}
|
||||
}, status=500)
|
||||
self.assertEqual(res.status_code, 500)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_ERROR, body.status)
|
||||
self.assertIn("Error: Error solving the challenge. Message: unknown error: net::ERR_PROXY_CONNECTION_FAILED",
|
||||
body.message)
|
||||
self.assertGreater(body.startTimestamp, 10000)
|
||||
self.assertGreaterEqual(body.endTimestamp, body.startTimestamp)
|
||||
self.assertEqual(utils.get_flaresolverr_version(), body.version)
|
||||
|
||||
def test_v1_endpoint_request_get_fail_timeout(self):
|
||||
res = self.app.post_json('/v1', {
|
||||
@ -401,6 +556,20 @@ class TestFlareSolverr(unittest.TestCase):
|
||||
self.assertEqual("Session created successfully.", body.message)
|
||||
self.assertEqual(body.session, "test_create_session")
|
||||
|
||||
def test_v1_endpoint_sessions_create_with_proxy(self):
|
||||
res = self.app.post_json('/v1', {
|
||||
"cmd": "sessions.create",
|
||||
"proxy": {
|
||||
"url": self.proxy_url
|
||||
}
|
||||
})
|
||||
self.assertEqual(res.status_code, 200)
|
||||
|
||||
body = V1ResponseBase(res.json)
|
||||
self.assertEqual(STATUS_OK, body.status)
|
||||
self.assertEqual("Session created successfully.", body.message)
|
||||
self.assertIsNotNone(body.session)
|
||||
|
||||
def test_v1_endpoint_sessions_list(self):
|
||||
self.app.post_json('/v1', {
|
||||
"cmd": "sessions.create",
|
||||
|
@ -39,6 +39,8 @@ def asset_cloudflare_solution(self, res, site_url, site_text):
|
||||
|
||||
class TestFlareSolverr(unittest.TestCase):
|
||||
app = TestApp(flaresolverr.app)
|
||||
# wait until the server is ready
|
||||
app.get('/')
|
||||
|
||||
def test_v1_endpoint_request_get_cloudflare(self):
|
||||
sites_get = [
|
||||
|
@ -17,11 +17,12 @@ by UltrafunkAmsterdam (https://github.com/ultrafunkamsterdam)
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
__version__ = "3.4.6"
|
||||
__version__ = "3.5.5"
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import pathlib
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
@ -33,7 +34,7 @@ from weakref import finalize
|
||||
import selenium.webdriver.chrome.service
|
||||
import selenium.webdriver.chrome.webdriver
|
||||
from selenium.webdriver.common.by import By
|
||||
import selenium.webdriver.common.service
|
||||
import selenium.webdriver.chromium.service
|
||||
import selenium.webdriver.remote.command
|
||||
import selenium.webdriver.remote.webdriver
|
||||
|
||||
@ -109,11 +110,11 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
browser_executable_path=None,
|
||||
port=0,
|
||||
enable_cdp_events=False,
|
||||
service_args=None,
|
||||
service_creationflags=None,
|
||||
# service_args=None,
|
||||
# service_creationflags=None,
|
||||
desired_capabilities=None,
|
||||
advanced_elements=False,
|
||||
service_log_path=None,
|
||||
# service_log_path=None,
|
||||
keep_alive=True,
|
||||
log_level=0,
|
||||
headless=False,
|
||||
@ -122,8 +123,9 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
suppress_welcome=True,
|
||||
use_subprocess=False,
|
||||
debug=False,
|
||||
no_sandbox=True,
|
||||
no_sandbox=True,
|
||||
windows_headless=False,
|
||||
user_multi_procs: bool = False,
|
||||
**kw,
|
||||
):
|
||||
"""
|
||||
@ -235,6 +237,14 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
uses the --no-sandbox option, and additionally does suppress the "unsecure option" status bar
|
||||
this option has a default of True since many people seem to run this as root (....) , and chrome does not start
|
||||
when running as root without using --no-sandbox flag.
|
||||
|
||||
user_multi_procs:
|
||||
set to true when you are using multithreads/multiprocessing
|
||||
ensures not all processes are trying to modify a binary which is in use by another.
|
||||
for this to work. YOU MUST HAVE AT LEAST 1 UNDETECTED_CHROMEDRIVER BINARY IN YOUR ROAMING DATA FOLDER.
|
||||
this requirement can be easily satisfied, by just running this program "normal" and close/kill it.
|
||||
|
||||
|
||||
"""
|
||||
|
||||
finalize(self, self._ensure_close, self)
|
||||
@ -243,8 +253,11 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
executable_path=driver_executable_path,
|
||||
force=patcher_force_close,
|
||||
version_main=version_main,
|
||||
user_multi_procs=user_multi_procs,
|
||||
)
|
||||
# self.patcher.auto(user_multiprocess = user_multi_num_procs)
|
||||
self.patcher.auto()
|
||||
|
||||
# self.patcher = patcher
|
||||
if not options:
|
||||
options = ChromeOptions()
|
||||
@ -361,6 +374,18 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
browser_executable_path or find_chrome_executable()
|
||||
)
|
||||
|
||||
if not options.binary_location or not \
|
||||
pathlib.Path(options.binary_location).exists():
|
||||
raise FileNotFoundError(
|
||||
"\n---------------------\n"
|
||||
"Could not determine browser executable."
|
||||
"\n---------------------\n"
|
||||
"Make sure your browser is installed in the default location (path).\n"
|
||||
"If you are sure about the browser executable, you can specify it using\n"
|
||||
"the `browser_executable_path='{}` parameter.\n\n"
|
||||
.format("/path/to/browser/executable" if IS_POSIX else "c:/path/to/your/browser.exe")
|
||||
)
|
||||
|
||||
self._delay = 3
|
||||
|
||||
self.user_data_dir = user_data_dir
|
||||
@ -371,11 +396,17 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
if no_sandbox:
|
||||
options.arguments.extend(["--no-sandbox", "--test-type"])
|
||||
|
||||
if headless or options.headless:
|
||||
v_main = int(self.patcher.version_main) if self.patcher.version_main else 108
|
||||
if v_main < 108:
|
||||
options.add_argument("--headless=chrome")
|
||||
elif v_main >= 108:
|
||||
if headless or getattr(options, 'headless', None):
|
||||
#workaround until a better checking is found
|
||||
try:
|
||||
v_main = int(self.patcher.version_main) if self.patcher.version_main else 108
|
||||
if v_main < 108:
|
||||
options.add_argument("--headless=chrome")
|
||||
elif v_main >= 108:
|
||||
options.add_argument("--headless=new")
|
||||
except:
|
||||
logger.warning("could not detect version_main."
|
||||
"therefore, we are assuming it is chrome 108 or higher")
|
||||
options.add_argument("--headless=new")
|
||||
|
||||
options.add_argument("--window-size=1920,1080")
|
||||
@ -419,40 +450,31 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
self.browser_pid = start_detached(
|
||||
options.binary_location, *options.arguments
|
||||
)
|
||||
else:
|
||||
startupinfo = subprocess.STARTUPINFO()
|
||||
if os.name == 'nt' and windows_headless:
|
||||
else:
|
||||
startupinfo = None
|
||||
if os.name == 'nt' and windows_headless:
|
||||
# STARTUPINFO() is Windows only
|
||||
startupinfo = subprocess.STARTUPINFO()
|
||||
startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
|
||||
browser = subprocess.Popen(
|
||||
[options.binary_location, *options.arguments],
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
close_fds=IS_POSIX,
|
||||
close_fds=IS_POSIX,
|
||||
startupinfo=startupinfo
|
||||
)
|
||||
self.browser_pid = browser.pid
|
||||
|
||||
if service_creationflags:
|
||||
service = selenium.webdriver.common.service.Service(
|
||||
self.patcher.executable_path, port, service_args, service_log_path
|
||||
)
|
||||
for attr_name in ("creationflags", "creation_flags"):
|
||||
if hasattr(service, attr_name):
|
||||
setattr(service, attr_name, service_creationflags)
|
||||
break
|
||||
else:
|
||||
service = None
|
||||
|
||||
service = selenium.webdriver.chromium.service.ChromiumService(
|
||||
self.patcher.executable_path
|
||||
)
|
||||
|
||||
super(Chrome, self).__init__(
|
||||
executable_path=self.patcher.executable_path,
|
||||
port=port,
|
||||
service=service,
|
||||
options=options,
|
||||
service_args=service_args,
|
||||
desired_capabilities=desired_capabilities,
|
||||
service_log_path=service_log_path,
|
||||
keep_alive=keep_alive,
|
||||
service=service, # needed or the service will be re-created
|
||||
)
|
||||
|
||||
self.reactor = None
|
||||
@ -471,7 +493,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
else:
|
||||
self._web_element_cls = WebElement
|
||||
|
||||
if options.headless:
|
||||
if headless or getattr(options, 'headless', None):
|
||||
self._configure_headless()
|
||||
|
||||
def _configure_headless(self):
|
||||
@ -485,8 +507,6 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
"Page.addScriptToEvaluateOnNewDocument",
|
||||
{
|
||||
"source": """
|
||||
|
||||
Object.defineProperty(window, "navigator", {
|
||||
Object.defineProperty(window, "navigator", {
|
||||
value: new Proxy(navigator, {
|
||||
has: (target, key) => (key === "webdriver" ? false : key in target),
|
||||
@ -708,13 +728,50 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
if not capabilities:
|
||||
capabilities = self.options.to_capabilities()
|
||||
super(selenium.webdriver.chrome.webdriver.WebDriver, self).start_session(
|
||||
capabilities, browser_profile
|
||||
capabilities
|
||||
)
|
||||
# super(Chrome, self).start_session(capabilities, browser_profile)
|
||||
|
||||
def find_elements_recursive(self, by, value):
|
||||
"""
|
||||
find elements in all frames
|
||||
this is a generator function, which is needed
|
||||
since if it would return a list of elements, they
|
||||
will be stale on arrival.
|
||||
using generator, when the element is returned we are in the correct frame
|
||||
to use it directly
|
||||
Args:
|
||||
by: By
|
||||
value: str
|
||||
Returns: Generator[webelement.WebElement]
|
||||
"""
|
||||
def search_frame(f=None):
|
||||
if not f:
|
||||
# ensure we are on main content frame
|
||||
self.switch_to.default_content()
|
||||
else:
|
||||
self.switch_to.frame(f)
|
||||
for elem in self.find_elements(by, value):
|
||||
yield elem
|
||||
# switch back to main content, otherwise we will get StaleElementReferenceException
|
||||
self.switch_to.default_content()
|
||||
|
||||
# search root frame
|
||||
for elem in search_frame():
|
||||
yield elem
|
||||
# get iframes
|
||||
frames = self.find_elements('css selector', 'iframe')
|
||||
|
||||
# search per frame
|
||||
for f in frames:
|
||||
for elem in search_frame(f):
|
||||
yield elem
|
||||
|
||||
def quit(self):
|
||||
try:
|
||||
self.service.process.kill()
|
||||
self.service.stop()
|
||||
self.service.process.kill()
|
||||
self.command_executor.close()
|
||||
self.service.process.wait(5)
|
||||
logger.debug("webdriver process ended")
|
||||
except (AttributeError, RuntimeError, OSError):
|
||||
@ -728,7 +785,7 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
os.kill(self.browser_pid, 15)
|
||||
logger.debug("gracefully closed browser")
|
||||
except Exception as e: # noqa
|
||||
logger.debug(e, exc_info=True)
|
||||
pass
|
||||
if (
|
||||
hasattr(self, "keep_user_data_dir")
|
||||
and hasattr(self, "user_data_dir")
|
||||
@ -747,7 +804,11 @@ class Chrome(selenium.webdriver.chrome.webdriver.WebDriver):
|
||||
else:
|
||||
logger.debug("successfully removed %s" % self.user_data_dir)
|
||||
break
|
||||
time.sleep(0.1)
|
||||
|
||||
try:
|
||||
time.sleep(0.1)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
# dereference patcher, so patcher can start cleaning up as well.
|
||||
# this must come last, otherwise it will throw 'in use' errors
|
||||
@ -842,10 +903,10 @@ def find_chrome_executable():
|
||||
if item is not None:
|
||||
for subitem in (
|
||||
"Google/Chrome/Application",
|
||||
"Google/Chrome Beta/Application",
|
||||
"Google/Chrome Canary/Application",
|
||||
):
|
||||
candidates.add(os.sep.join((item, subitem, "chrome.exe")))
|
||||
for candidate in candidates:
|
||||
logger.debug('checking if %s exists and is executable' % candidate)
|
||||
if os.path.exists(candidate) and os.access(candidate, os.X_OK):
|
||||
logger.debug('found! using %s' % candidate)
|
||||
return os.path.normpath(candidate)
|
||||
|
@ -2,6 +2,7 @@ import asyncio
|
||||
from collections.abc import Mapping
|
||||
from collections.abc import Sequence
|
||||
from functools import wraps
|
||||
import os
|
||||
import logging
|
||||
import threading
|
||||
import time
|
||||
@ -187,4 +188,6 @@ def test():
|
||||
|
||||
time.sleep(10)
|
||||
|
||||
if os.name == "nt":
|
||||
driver.close()
|
||||
driver.quit()
|
||||
|
@ -41,6 +41,7 @@ def start_detached(executable, *args):
|
||||
# close pipes
|
||||
writer.close()
|
||||
reader.close()
|
||||
process.close()
|
||||
|
||||
return pid
|
||||
|
||||
|
@ -3,39 +3,32 @@
|
||||
|
||||
from distutils.version import LooseVersion
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import pathlib
|
||||
import platform
|
||||
import random
|
||||
import re
|
||||
import shutil
|
||||
import string
|
||||
import sys
|
||||
import time
|
||||
from urllib.request import urlopen
|
||||
from urllib.request import urlretrieve
|
||||
import zipfile
|
||||
|
||||
from multiprocessing import Lock
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
IS_POSIX = sys.platform.startswith(("darwin", "cygwin", "linux", "linux2"))
|
||||
IS_POSIX = sys.platform.startswith(("darwin", "cygwin", "linux", "linux2", "freebsd"))
|
||||
|
||||
|
||||
class Patcher(object):
|
||||
url_repo = "https://chromedriver.storage.googleapis.com"
|
||||
zip_name = "chromedriver_%s.zip"
|
||||
lock = Lock()
|
||||
exe_name = "chromedriver%s"
|
||||
|
||||
platform = sys.platform
|
||||
if platform.endswith("win32"):
|
||||
zip_name %= "win32"
|
||||
exe_name %= ".exe"
|
||||
if platform.endswith(("linux", "linux2")):
|
||||
zip_name %= "linux64"
|
||||
exe_name %= ""
|
||||
if platform.endswith("darwin"):
|
||||
zip_name %= "mac64"
|
||||
exe_name %= ""
|
||||
|
||||
if platform.endswith("win32"):
|
||||
d = "~/appdata/roaming/undetected_chromedriver"
|
||||
elif "LAMBDA_TASK_ROOT" in os.environ:
|
||||
@ -48,7 +41,13 @@ class Patcher(object):
|
||||
d = "~/.undetected_chromedriver"
|
||||
data_path = os.path.abspath(os.path.expanduser(d))
|
||||
|
||||
def __init__(self, executable_path=None, force=False, version_main: int = 0):
|
||||
def __init__(
|
||||
self,
|
||||
executable_path=None,
|
||||
force=False,
|
||||
version_main: int = 0,
|
||||
user_multi_procs=False,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
executable_path: None = automatic
|
||||
@ -61,14 +60,36 @@ class Patcher(object):
|
||||
self.force = force
|
||||
self._custom_exe_path = False
|
||||
prefix = "undetected"
|
||||
self.user_multi_procs = user_multi_procs
|
||||
|
||||
try:
|
||||
# Try to convert version_main into an integer
|
||||
version_main_int = int(version_main)
|
||||
# check if version_main_int is less than or equal to e.g 114
|
||||
self.is_old_chromedriver = version_main and version_main_int <= 114
|
||||
except (ValueError,TypeError):
|
||||
# Check not running inside Docker
|
||||
if not os.path.exists("/app/chromedriver"):
|
||||
# If the conversion fails, log an error message
|
||||
logging.info("version_main cannot be converted to an integer")
|
||||
# Set self.is_old_chromedriver to False if the conversion fails
|
||||
self.is_old_chromedriver = False
|
||||
|
||||
# Needs to be called before self.exe_name is accessed
|
||||
self._set_platform_name()
|
||||
|
||||
if not os.path.exists(self.data_path):
|
||||
os.makedirs(self.data_path, exist_ok=True)
|
||||
|
||||
if not executable_path:
|
||||
self.executable_path = os.path.join(
|
||||
self.data_path, "_".join([prefix, self.exe_name])
|
||||
)
|
||||
if sys.platform.startswith("freebsd"):
|
||||
self.executable_path = os.path.join(
|
||||
self.data_path, self.exe_name
|
||||
)
|
||||
else:
|
||||
self.executable_path = os.path.join(
|
||||
self.data_path, "_".join([prefix, self.exe_name])
|
||||
)
|
||||
|
||||
if not IS_POSIX:
|
||||
if executable_path:
|
||||
@ -78,17 +99,67 @@ class Patcher(object):
|
||||
self.zip_path = os.path.join(self.data_path, prefix)
|
||||
|
||||
if not executable_path:
|
||||
self.executable_path = os.path.abspath(
|
||||
os.path.join(".", self.executable_path)
|
||||
)
|
||||
if not self.user_multi_procs:
|
||||
self.executable_path = os.path.abspath(
|
||||
os.path.join(".", self.executable_path)
|
||||
)
|
||||
|
||||
if executable_path:
|
||||
self._custom_exe_path = True
|
||||
self.executable_path = executable_path
|
||||
|
||||
# Set the correct repository to download the Chromedriver from
|
||||
if self.is_old_chromedriver:
|
||||
self.url_repo = "https://chromedriver.storage.googleapis.com"
|
||||
else:
|
||||
self.url_repo = "https://googlechromelabs.github.io/chrome-for-testing"
|
||||
|
||||
self.version_main = version_main
|
||||
self.version_full = None
|
||||
|
||||
def auto(self, executable_path=None, force=False, version_main=None):
|
||||
def _set_platform_name(self):
|
||||
"""
|
||||
Set the platform and exe name based on the platform undetected_chromedriver is running on
|
||||
in order to download the correct chromedriver.
|
||||
"""
|
||||
if self.platform.endswith("win32"):
|
||||
self.platform_name = "win32"
|
||||
self.exe_name %= ".exe"
|
||||
if self.platform.endswith(("linux", "linux2")):
|
||||
self.platform_name = "linux64"
|
||||
self.exe_name %= ""
|
||||
if self.platform.endswith("darwin"):
|
||||
if self.is_old_chromedriver:
|
||||
self.platform_name = "mac64"
|
||||
else:
|
||||
self.platform_name = "mac-x64"
|
||||
self.exe_name %= ""
|
||||
if self.platform.startswith("freebsd"):
|
||||
self.platform_name = "freebsd"
|
||||
self.exe_name %= ""
|
||||
|
||||
def auto(self, executable_path=None, force=False, version_main=None, _=None):
|
||||
"""
|
||||
|
||||
Args:
|
||||
executable_path:
|
||||
force:
|
||||
version_main:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
p = pathlib.Path(self.data_path)
|
||||
if self.user_multi_procs:
|
||||
with Lock():
|
||||
files = list(p.rglob("*chromedriver*"))
|
||||
most_recent = max(files, key=lambda f: f.stat().st_mtime)
|
||||
files.remove(most_recent)
|
||||
list(map(lambda f: f.unlink(), files))
|
||||
if self.is_binary_patched(most_recent):
|
||||
self.executable_path = str(most_recent)
|
||||
return True
|
||||
|
||||
if executable_path:
|
||||
self.executable_path = executable_path
|
||||
self._custom_exe_path = True
|
||||
@ -105,27 +176,104 @@ class Patcher(object):
|
||||
if force is True:
|
||||
self.force = force
|
||||
|
||||
try:
|
||||
os.unlink(self.executable_path)
|
||||
except PermissionError:
|
||||
if self.force:
|
||||
self.force_kill_instances(self.executable_path)
|
||||
return self.auto(force=not self.force)
|
||||
|
||||
if self.platform_name == "freebsd":
|
||||
chromedriver_path = shutil.which("chromedriver")
|
||||
|
||||
if not os.path.isfile(chromedriver_path) or not os.access(chromedriver_path, os.X_OK):
|
||||
logging.error("Chromedriver not installed!")
|
||||
return
|
||||
|
||||
version_path = os.path.join(os.path.dirname(self.executable_path), "version.txt")
|
||||
|
||||
process = os.popen(f'"{chromedriver_path}" --version')
|
||||
chromedriver_version = process.read().split(' ')[1].split(' ')[0]
|
||||
process.close()
|
||||
|
||||
current_version = None
|
||||
if os.path.isfile(version_path) or os.access(version_path, os.X_OK):
|
||||
with open(version_path, 'r') as f:
|
||||
current_version = f.read()
|
||||
|
||||
if current_version != chromedriver_version:
|
||||
logging.info("Copying chromedriver executable...")
|
||||
shutil.copy(chromedriver_path, self.executable_path)
|
||||
os.chmod(self.executable_path, 0o755)
|
||||
|
||||
with open(version_path, 'w') as f:
|
||||
f.write(chromedriver_version)
|
||||
|
||||
logging.info("Chromedriver executable copied!")
|
||||
else:
|
||||
try:
|
||||
if self.is_binary_patched():
|
||||
# assumes already running AND patched
|
||||
return True
|
||||
os.unlink(self.executable_path)
|
||||
except PermissionError:
|
||||
if self.force:
|
||||
self.force_kill_instances(self.executable_path)
|
||||
return self.auto(force=not self.force)
|
||||
try:
|
||||
if self.is_binary_patched():
|
||||
# assumes already running AND patched
|
||||
return True
|
||||
except PermissionError:
|
||||
pass
|
||||
# return False
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
# return False
|
||||
except FileNotFoundError:
|
||||
|
||||
release = self.fetch_release_number()
|
||||
self.version_main = release.version[0]
|
||||
self.version_full = release
|
||||
self.unzip_package(self.fetch_package())
|
||||
|
||||
return self.patch()
|
||||
|
||||
def driver_binary_in_use(self, path: str = None) -> bool:
|
||||
"""
|
||||
naive test to check if a found chromedriver binary is
|
||||
currently in use
|
||||
|
||||
Args:
|
||||
path: a string or PathLike object to the binary to check.
|
||||
if not specified, we check use this object's executable_path
|
||||
"""
|
||||
if not path:
|
||||
path = self.executable_path
|
||||
p = pathlib.Path(path)
|
||||
|
||||
if not p.exists():
|
||||
raise OSError("file does not exist: %s" % p)
|
||||
try:
|
||||
with open(p, mode="a+b") as fs:
|
||||
exc = []
|
||||
try:
|
||||
|
||||
fs.seek(0, 0)
|
||||
except PermissionError as e:
|
||||
exc.append(e) # since some systems apprently allow seeking
|
||||
# we conduct another test
|
||||
try:
|
||||
fs.readline()
|
||||
except PermissionError as e:
|
||||
exc.append(e)
|
||||
|
||||
if exc:
|
||||
|
||||
return True
|
||||
return False
|
||||
# ok safe to assume this is in use
|
||||
except Exception as e:
|
||||
# logger.exception("whoops ", e)
|
||||
pass
|
||||
|
||||
release = self.fetch_release_number()
|
||||
self.version_main = release.version[0]
|
||||
self.version_full = release
|
||||
self.unzip_package(self.fetch_package())
|
||||
return self.patch()
|
||||
def cleanup_unused_files(self):
|
||||
p = pathlib.Path(self.data_path)
|
||||
items = list(p.glob("*undetected*"))
|
||||
for item in items:
|
||||
try:
|
||||
item.unlink()
|
||||
except:
|
||||
pass
|
||||
|
||||
def patch(self):
|
||||
self.patch_exe()
|
||||
@ -137,12 +285,32 @@ class Patcher(object):
|
||||
:return: version string
|
||||
:rtype: LooseVersion
|
||||
"""
|
||||
path = "/latest_release"
|
||||
if self.version_main:
|
||||
path += f"_{self.version_main}"
|
||||
path = path.upper()
|
||||
# Endpoint for old versions of Chromedriver (114 and below)
|
||||
if self.is_old_chromedriver:
|
||||
path = f"/latest_release_{self.version_main}"
|
||||
path = path.upper()
|
||||
logger.debug("getting release number from %s" % path)
|
||||
return LooseVersion(urlopen(self.url_repo + path).read().decode())
|
||||
|
||||
# Endpoint for new versions of Chromedriver (115+)
|
||||
if not self.version_main:
|
||||
# Fetch the latest version
|
||||
path = "/last-known-good-versions-with-downloads.json"
|
||||
logger.debug("getting release number from %s" % path)
|
||||
with urlopen(self.url_repo + path) as conn:
|
||||
response = conn.read().decode()
|
||||
|
||||
last_versions = json.loads(response)
|
||||
return LooseVersion(last_versions["channels"]["Stable"]["version"])
|
||||
|
||||
# Fetch the latest minor version of the major version provided
|
||||
path = "/latest-versions-per-milestone-with-downloads.json"
|
||||
logger.debug("getting release number from %s" % path)
|
||||
return LooseVersion(urlopen(self.url_repo + path).read().decode())
|
||||
with urlopen(self.url_repo + path) as conn:
|
||||
response = conn.read().decode()
|
||||
|
||||
major_versions = json.loads(response)
|
||||
return LooseVersion(major_versions["milestones"][str(self.version_main)]["version"])
|
||||
|
||||
def parse_exe_version(self):
|
||||
with io.open(self.executable_path, "rb") as f:
|
||||
@ -157,10 +325,16 @@ class Patcher(object):
|
||||
|
||||
:return: path to downloaded file
|
||||
"""
|
||||
u = "%s/%s/%s" % (self.url_repo, self.version_full.vstring, self.zip_name)
|
||||
logger.debug("downloading from %s" % u)
|
||||
# return urlretrieve(u, filename=self.data_path)[0]
|
||||
return urlretrieve(u)[0]
|
||||
zip_name = f"chromedriver_{self.platform_name}.zip"
|
||||
if self.is_old_chromedriver:
|
||||
download_url = "%s/%s/%s" % (self.url_repo, self.version_full.vstring, zip_name)
|
||||
else:
|
||||
zip_name = zip_name.replace("_", "-", 1)
|
||||
download_url = "https://storage.googleapis.com/chrome-for-testing-public/%s/%s/%s"
|
||||
download_url %= (self.version_full.vstring, self.platform_name, zip_name)
|
||||
|
||||
logger.debug("downloading from %s" % download_url)
|
||||
return urlretrieve(download_url)[0]
|
||||
|
||||
def unzip_package(self, fp):
|
||||
"""
|
||||
@ -168,6 +342,12 @@ class Patcher(object):
|
||||
|
||||
:return: path to unpacked executable
|
||||
"""
|
||||
exe_path = self.exe_name
|
||||
if not self.is_old_chromedriver:
|
||||
# The new chromedriver unzips into its own folder
|
||||
zip_name = f"chromedriver-{self.platform_name}"
|
||||
exe_path = os.path.join(zip_name, self.exe_name)
|
||||
|
||||
logger.debug("unzipping %s" % fp)
|
||||
try:
|
||||
os.unlink(self.zip_path)
|
||||
@ -176,10 +356,10 @@ class Patcher(object):
|
||||
|
||||
os.makedirs(self.zip_path, mode=0o755, exist_ok=True)
|
||||
with zipfile.ZipFile(fp, mode="r") as zf:
|
||||
zf.extract(self.exe_name, self.zip_path)
|
||||
os.rename(os.path.join(self.zip_path, self.exe_name), self.executable_path)
|
||||
zf.extractall(self.zip_path)
|
||||
os.rename(os.path.join(self.zip_path, exe_path), self.executable_path)
|
||||
os.remove(fp)
|
||||
os.rmdir(self.zip_path)
|
||||
shutil.rmtree
|
||||
os.chmod(self.executable_path, 0o755)
|
||||
return self.executable_path
|
||||
|
||||
@ -255,21 +435,17 @@ class Patcher(object):
|
||||
else:
|
||||
timeout = 3 # stop trying after this many seconds
|
||||
t = time.monotonic()
|
||||
while True:
|
||||
now = time.monotonic()
|
||||
if now - t > timeout:
|
||||
# we don't want to wait until the end of time
|
||||
logger.debug(
|
||||
"could not unlink %s in time (%d seconds)"
|
||||
% (self.executable_path, timeout)
|
||||
)
|
||||
break
|
||||
now = lambda: time.monotonic()
|
||||
while now() - t > timeout:
|
||||
# we don't want to wait until the end of time
|
||||
try:
|
||||
if self.user_multi_procs:
|
||||
break
|
||||
os.unlink(self.executable_path)
|
||||
logger.debug("successfully unlinked %s" % self.executable_path)
|
||||
break
|
||||
except (OSError, RuntimeError, PermissionError):
|
||||
time.sleep(0.1)
|
||||
time.sleep(0.01)
|
||||
continue
|
||||
except FileNotFoundError:
|
||||
break
|
||||
|
150
src/utils.py
150
src/utils.py
@ -1,13 +1,18 @@
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
import urllib.parse
|
||||
|
||||
from selenium.webdriver.chrome.webdriver import WebDriver
|
||||
import undetected_chromedriver as uc
|
||||
|
||||
FLARESOLVERR_VERSION = None
|
||||
PLATFORM_VERSION = None
|
||||
CHROME_EXE_PATH = None
|
||||
CHROME_MAJOR_VERSION = None
|
||||
USER_AGENT = None
|
||||
@ -35,27 +40,133 @@ def get_flaresolverr_version() -> str:
|
||||
FLARESOLVERR_VERSION = json.loads(f.read())['version']
|
||||
return FLARESOLVERR_VERSION
|
||||
|
||||
def get_current_platform() -> str:
|
||||
global PLATFORM_VERSION
|
||||
if PLATFORM_VERSION is not None:
|
||||
return PLATFORM_VERSION
|
||||
PLATFORM_VERSION = os.name
|
||||
return PLATFORM_VERSION
|
||||
|
||||
def get_webdriver() -> WebDriver:
|
||||
global PATCHED_DRIVER_PATH
|
||||
|
||||
def create_proxy_extension(proxy: dict) -> str:
|
||||
parsed_url = urllib.parse.urlparse(proxy['url'])
|
||||
scheme = parsed_url.scheme
|
||||
host = parsed_url.hostname
|
||||
port = parsed_url.port
|
||||
username = proxy['username']
|
||||
password = proxy['password']
|
||||
manifest_json = """
|
||||
{
|
||||
"version": "1.0.0",
|
||||
"manifest_version": 2,
|
||||
"name": "Chrome Proxy",
|
||||
"permissions": [
|
||||
"proxy",
|
||||
"tabs",
|
||||
"unlimitedStorage",
|
||||
"storage",
|
||||
"<all_urls>",
|
||||
"webRequest",
|
||||
"webRequestBlocking"
|
||||
],
|
||||
"background": {"scripts": ["background.js"]},
|
||||
"minimum_chrome_version": "76.0.0"
|
||||
}
|
||||
"""
|
||||
|
||||
background_js = """
|
||||
var config = {
|
||||
mode: "fixed_servers",
|
||||
rules: {
|
||||
singleProxy: {
|
||||
scheme: "%s",
|
||||
host: "%s",
|
||||
port: %d
|
||||
},
|
||||
bypassList: ["localhost"]
|
||||
}
|
||||
};
|
||||
|
||||
chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});
|
||||
|
||||
function callbackFn(details) {
|
||||
return {
|
||||
authCredentials: {
|
||||
username: "%s",
|
||||
password: "%s"
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
chrome.webRequest.onAuthRequired.addListener(
|
||||
callbackFn,
|
||||
{ urls: ["<all_urls>"] },
|
||||
['blocking']
|
||||
);
|
||||
""" % (
|
||||
scheme,
|
||||
host,
|
||||
port,
|
||||
username,
|
||||
password
|
||||
)
|
||||
|
||||
proxy_extension_dir = tempfile.mkdtemp()
|
||||
|
||||
with open(os.path.join(proxy_extension_dir, "manifest.json"), "w") as f:
|
||||
f.write(manifest_json)
|
||||
|
||||
with open(os.path.join(proxy_extension_dir, "background.js"), "w") as f:
|
||||
f.write(background_js)
|
||||
|
||||
return proxy_extension_dir
|
||||
|
||||
|
||||
def get_webdriver(proxy: dict = None) -> WebDriver:
|
||||
global PATCHED_DRIVER_PATH, USER_AGENT
|
||||
logging.debug('Launching web browser...')
|
||||
|
||||
# undetected_chromedriver
|
||||
options = uc.ChromeOptions()
|
||||
options.add_argument('--no-sandbox')
|
||||
options.add_argument('--window-size=1920,1080')
|
||||
options.add_argument('--disable-search-engine-choice-screen')
|
||||
# todo: this param shows a warning in chrome head-full
|
||||
options.add_argument('--disable-setuid-sandbox')
|
||||
options.add_argument('--disable-dev-shm-usage')
|
||||
# this option removes the zygote sandbox (it seems that the resolution is a bit faster)
|
||||
options.add_argument('--no-zygote')
|
||||
# attempt to fix Docker ARM32 build
|
||||
options.add_argument('--disable-gpu-sandbox')
|
||||
options.add_argument('--disable-software-rasterizer')
|
||||
IS_ARMARCH = platform.machine().startswith(('arm', 'aarch'))
|
||||
if IS_ARMARCH:
|
||||
options.add_argument('--disable-gpu-sandbox')
|
||||
options.add_argument('--disable-software-rasterizer')
|
||||
options.add_argument('--ignore-certificate-errors')
|
||||
options.add_argument('--ignore-ssl-errors')
|
||||
# fix GL errors in ASUSTOR NAS
|
||||
# https://github.com/FlareSolverr/FlareSolverr/issues/782
|
||||
# https://github.com/microsoft/vscode/issues/127800#issuecomment-873342069
|
||||
# https://peter.sh/experiments/chromium-command-line-switches/#use-gl
|
||||
options.add_argument('--use-gl=swiftshader')
|
||||
|
||||
# note: headless mode is detected (options.headless = True)
|
||||
language = os.environ.get('LANG', None)
|
||||
if language is not None:
|
||||
options.add_argument('--accept-lang=%s' % language)
|
||||
|
||||
# Fix for Chrome 117 | https://github.com/FlareSolverr/FlareSolverr/issues/910
|
||||
if USER_AGENT is not None:
|
||||
options.add_argument('--user-agent=%s' % USER_AGENT)
|
||||
|
||||
proxy_extension_dir = None
|
||||
if proxy and all(key in proxy for key in ['url', 'username', 'password']):
|
||||
proxy_extension_dir = create_proxy_extension(proxy)
|
||||
options.add_argument("--load-extension=%s" % os.path.abspath(proxy_extension_dir))
|
||||
elif proxy and 'url' in proxy:
|
||||
proxy_url = proxy['url']
|
||||
logging.debug("Using webdriver proxy: %s", proxy_url)
|
||||
options.add_argument('--proxy-server=%s' % proxy_url)
|
||||
|
||||
# note: headless mode is detected (headless = True)
|
||||
# we launch the browser in head-full mode with the window hidden
|
||||
windows_headless = False
|
||||
if get_config_headless():
|
||||
@ -63,6 +174,8 @@ def get_webdriver() -> WebDriver:
|
||||
windows_headless = True
|
||||
else:
|
||||
start_xvfb_display()
|
||||
# For normal headless mode:
|
||||
# options.add_argument('--headless')
|
||||
|
||||
# if we are inside the Docker container, we avoid downloading the driver
|
||||
driver_exe_path = None
|
||||
@ -80,14 +193,22 @@ def get_webdriver() -> WebDriver:
|
||||
|
||||
# downloads and patches the chromedriver
|
||||
# if we don't set driver_executable_path it downloads, patches, and deletes the driver each time
|
||||
driver = uc.Chrome(options=options, browser_executable_path=browser_executable_path,
|
||||
driver_executable_path=driver_exe_path, version_main=version_main,
|
||||
windows_headless=windows_headless)
|
||||
try:
|
||||
driver = uc.Chrome(options=options, browser_executable_path=browser_executable_path,
|
||||
driver_executable_path=driver_exe_path, version_main=version_main,
|
||||
windows_headless=windows_headless, headless=get_config_headless())
|
||||
except Exception as e:
|
||||
logging.error("Error starting Chrome: %s" % e)
|
||||
|
||||
# save the patched driver to avoid re-downloads
|
||||
if driver_exe_path is None:
|
||||
PATCHED_DRIVER_PATH = os.path.join(driver.patcher.data_path, driver.patcher.exe_name)
|
||||
shutil.copy(driver.patcher.executable_path, PATCHED_DRIVER_PATH)
|
||||
if PATCHED_DRIVER_PATH != driver.patcher.executable_path:
|
||||
shutil.copy(driver.patcher.executable_path, PATCHED_DRIVER_PATH)
|
||||
|
||||
# clean up proxy extension directory
|
||||
if proxy_extension_dir is not None:
|
||||
shutil.rmtree(proxy_extension_dir)
|
||||
|
||||
# selenium vanilla
|
||||
# options = webdriver.ChromeOptions()
|
||||
@ -106,12 +227,15 @@ def get_chrome_exe_path() -> str:
|
||||
return CHROME_EXE_PATH
|
||||
# linux pyinstaller bundle
|
||||
chrome_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'chrome', "chrome")
|
||||
if os.path.exists(chrome_path) and os.access(chrome_path, os.X_OK):
|
||||
if os.path.exists(chrome_path):
|
||||
if not os.access(chrome_path, os.X_OK):
|
||||
raise Exception(f'Chrome binary "{chrome_path}" is not executable. '
|
||||
f'Please, extract the archive with "tar xzf <file.tar.gz>".')
|
||||
CHROME_EXE_PATH = chrome_path
|
||||
return CHROME_EXE_PATH
|
||||
# windows pyinstaller bundle
|
||||
chrome_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'chrome', "chrome.exe")
|
||||
if os.path.exists(chrome_path) and os.access(chrome_path, os.X_OK):
|
||||
if os.path.exists(chrome_path):
|
||||
CHROME_EXE_PATH = chrome_path
|
||||
return CHROME_EXE_PATH
|
||||
# system
|
||||
@ -193,11 +317,15 @@ def get_user_agent(driver=None) -> str:
|
||||
if driver is None:
|
||||
driver = get_webdriver()
|
||||
USER_AGENT = driver.execute_script("return navigator.userAgent")
|
||||
# Fix for Chrome 117 | https://github.com/FlareSolverr/FlareSolverr/issues/910
|
||||
USER_AGENT = re.sub('HEADLESS', '', USER_AGENT, flags=re.IGNORECASE)
|
||||
return USER_AGENT
|
||||
except Exception as e:
|
||||
raise Exception("Error getting browser User-Agent. " + str(e))
|
||||
finally:
|
||||
if driver is not None:
|
||||
if PLATFORM_VERSION == "nt":
|
||||
driver.close()
|
||||
driver.quit()
|
||||
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user