github/FlareSolverr
1
1
Fork 0
mirror of https://github.com/FlareSolverr/FlareSolverr.git synced 2025-06-08 20:45:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 14fb3610da8f1539d511a7fa14c0d6dfb3ffeef9 into f21c1d51bcdc322df5d4857391a9c43ef8850136

Browse Source
This commit is contained in:
WeatherControl 2025-06-05 01:13:45 +02:00 committed by GitHub
commit 88e4c6af7f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -188,6 +188,8 @@ session. When you no longer need to use a session you should make sure to close
| cookies | Optional. Will be used by the headless browser. Eg: `"cookies": [{"name": "cookie1", "value": "value1"}, {"name": "cookie2", "value": "value2"}]`. | | 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. | | 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`.) | | 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`.) |
| xpath | Optional, default disabled. XPath selector to JS rendered content. |
| xpathWaitTimeout | Optional, default disabled. Max timeout to wait for XPath selector in milliseconds. |
> **Warning** > **Warning**
> If you want to use Cloudflare clearance cookie in your scripts, make sure you use the FlareSolverr User-Agent too. If they don't match you will see the challenge. > If you want to use Cloudflare clearance cookie in your scripts, make sure you use the FlareSolverr User-Agent too. If they don't match you will see the challenge.
@ -259,6 +261,11 @@ This is the same as `request.get` but it takes one more param:
|-----------|--------------------------------------------------------------------------| |-----------|--------------------------------------------------------------------------|
| postData | Must be a string with `application/x-www-form-urlencoded`. Eg: `a=b&c=d` | | postData | Must be a string with `application/x-www-form-urlencoded`. Eg: `a=b&c=d` |
## JS Rendering
If you want to get HTML after JS Rendering, set "xpath" parameter to the request. You should set xpath selector that represents the content you want to get.
Also you can set xpathWaitTimeout parameter to control how much browser will wait for content.
## Environment variables ## Environment variables
| Name | Default | Notes | | Name | Default | Notes |

2
src/dtos.py
View File

@ -36,6 +36,8 @@ class V1RequestBase(object):
session_ttl_minutes: int = None session_ttl_minutes: int = None
headers: list = None # deprecated v2.0.0, not used headers: list = None # deprecated v2.0.0, not used
userAgent: str = None # deprecated v2.0.0, not used userAgent: str = None # deprecated v2.0.0, not used
xpath: str = None
xpathWaitTimeout: int = None
# V1Request # V1Request
url: str = None url: str = None

8
src/flaresolverr_service.py
View File

@ -123,6 +123,8 @@ def _controller_v1_handler(req: V1RequestBase) -> V1ResponseBase:
# set default values # set default values
if req.maxTimeout is None or int(req.maxTimeout) < 1: if req.maxTimeout is None or int(req.maxTimeout) < 1:
req.maxTimeout = 60000 req.maxTimeout = 60000
if req.xpathWaitTimeout is None or req.xpathWaitTimeout < 1:
req.xpathWaitTimeout = 60000
# execute the command # execute the command
res: V1ResponseBase res: V1ResponseBase
@ -390,6 +392,12 @@ def _evil_logic(req: V1RequestBase, driver: WebDriver, method: str) -> Challenge
if not req.returnOnlyCookies: if not req.returnOnlyCookies:
challenge_res.headers = {} # todo: fix, selenium not provides this info challenge_res.headers = {} # todo: fix, selenium not provides this info
if req.xpath:
try:
WebDriverWait(driver, req.xpathWaitTimeout / 1000)\
.until(presence_of_element_located((By.XPATH, req.xpath)))
except TimeoutException:
raise Exception(f'JS render timeout. Specified selector was not found in time.')
challenge_res.response = driver.page_source challenge_res.response = driver.page_source
res.result = challenge_res res.result = challenge_res