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

download: support download and return images

Browse Source 
Find all elements of tag '<img>' and retrun binary data as base64 encoded string

Signed-off-by: acg5159 <acg5159@gmail.com>
This commit is contained in:
acg5159 2025-05-01 13:08:20 -04:00
parent ce5369dd41
commit 622ea9a1af
1 changed files with 42 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
src/flaresolverr_service.py
View File

@ -2,9 +2,12 @@ import logging
import platform
import sys
import time
import requests
import os
import base64
from datetime import timedelta
from html import escape
from urllib.parse import unquote, quote
from urllib.parse import unquote, quote, urljoin, urlsplit
from func_timeout import FunctionTimedOut, func_timeout
from selenium.common import TimeoutException
@ -149,8 +152,6 @@ def _cmd_request_get(req: V1RequestBase) -> V1ResponseBase:
raise Exception("Cannot use 'postBody' when sending a GET request.")
if req.returnRawHtml is not None:
logging.warning("Request parameter 'returnRawHtml' was removed in FlareSolverr v2.")
if req.download is not None:
logging.warning("Request parameter 'download' was removed in FlareSolverr v2.")
challenge_res = _resolve_challenge(req, 'GET')
res = V1ResponseBase({})
@ -418,6 +419,44 @@ def _evil_logic(req: V1RequestBase, driver: WebDriver, method: str) -> Challenge
challenge_res.headers = {} # todo: fix, selenium not provides this info
challenge_res.response = driver.page_source
if req.download:
# todo: support XPATH
img_elements = driver.find_elements(By.TAG_NAME, "img")
resp = []
for img in img_elements:
try:
# todo: support other attribute
src = img.get_attribute("src")
if src:
img_url = urljoin(driver.current_url, src)
response = requests.get(img_url, timeout=10)
if response.status_code == 200:
logging.info(f"Found {img_url}")
filename = os.path.basename(urlsplit(img_url).path)
mime_type = response.headers.get("Content-Type", "image/jpeg")
b64_data = base64.b64encode(response.content).decode('utf-8')
r = {
"url": f"{img_url}",
"filename": f"{filename}",
"mime_type": f"{mime_type}",
"encoded_data": f"{b64_data}"
}
resp.append(r)
else:
logging.error(f"Invalid Repsonse Code ({response.status_code}): {img_url}")
except Exception as e:
logging.error(f"Error: {e}")
if not resp:
logging.error("No Images Found!")
res.message = "No Images Found!"
else:
logging.info(f"Found {len(resp)} Images!")
res.message = f"Found {len(resp)} Images!"
challenge_res.download = resp
res.result = challenge_res
return res