bellingcat/vk-url-scraper
1
0
Fork 0
mirror of https://github.com/bellingcat/vk-url-scraper.git synced 2026-06-08 03:18:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

captcha fix

Browse Source
This commit is contained in:
msramalho
2022-06-21 14:05:33 +02:00
parent db03a4c0f6
commit d96e0c0a3a
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vk_url_scraper/utils.py
View File

@@ -22,7 +22,7 @@ def mkdir_if_not_exists(folder):
def captcha_handler(captcha):
print(
f"""CAPTCHA DETECTED, please solve it and put the solution into the webpage specified in the 'CAPTCHA_HANDLE_URL' env variable in the next 2min. Put the answer in the format "{captcha.sid}=SOLUTION".
f"""CAPTCHA DETECTED, please solve it and put the solution into the webpage specified in the 'CAPTCHA_HANDLE_URL' env variable in the next 10min. Put the answer in the format "{captcha.sid}=SOLUTION".
{captcha.sid=}
{captcha.get_url()=}
@@ -32,18 +32,18 @@ def captcha_handler(captcha):
if "CAPTCHA_HANDLE_URL" in os.environ:
url = os.environ["CAPTCHA_HANDLE_URL"]
regex_string = re.compile(f"{captcha.sid}=(.*)")
for wait in 24 * [5]: # tries every 5s for 2min
for wait in (10 * 6) * [10]: # tries every 10s for 10min
print(f"sending request to {url=}", flush=True)
r = requests.get(url)
if r.status_code == 200:
print(f"got response {r.text=}", flush=True)
if key := regex_string.search(r.text):
print(f"got captcha result {key=}", flush=True)
print(f"got captcha result {key=} {key[1]=}", flush=True)
return captcha.try_again(key[1])
print(f"sleeping {wait} seconds", flush=True)
time.sleep(wait)
else:
key = input(f"Enter captcha code for {captcha.get_url()}:").strip()
return captcha.try_again(key[0])
return captcha.try_again(key)
return False