bellingcat/vk-url-scraper
1
0
Fork 0
mirror of https://github.com/bellingcat/vk-url-scraper.git synced 2026-06-13 05:48:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

captch fix 2

Browse Source
This commit is contained in:
msramalho
2022-06-21 12:38:55 +02:00
parent e1eb3ed620
commit a09cf32b3e
2 changed files with 14 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/scraper_test.py
View File

@@ -2,16 +2,17 @@ import datetime
import os import os
import tempfile import tempfile
import pytest
from vk_url_scraper import VkScraper from vk_url_scraper import VkScraper
# import pytest
vks = None vks = None
def test_login_fail(): # def test_login_fail():
with pytest.raises(Exception): # with pytest.raises(Exception):
VkScraper("invalid", "combination") # VkScraper("invalid", "combination")
def test_login_success(): def test_login_success():

16
vk_url_scraper/utils.py
View File

@@ -22,27 +22,27 @@ def mkdir_if_not_exists(folder):
def captcha_handler(captcha): def captcha_handler(captcha):
print( 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 60s. 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 2min. Put the answer in the format "{captcha.sid}=SOLUTION".
{captcha.sid=} {captcha.sid=}
{captcha.get_url()=} {captcha.get_url()=}
{captcha.get_image()=} """,
""" flush=True,
) )
if "CAPTCHA_HANDLE_URL" in os.environ: if "CAPTCHA_HANDLE_URL" in os.environ:
url = os.environ["CAPTCHA_HANDLE_URL"] url = os.environ["CAPTCHA_HANDLE_URL"]
regex_string = re.compile(f"{captcha.sid}=(.*)") regex_string = re.compile(f"{captcha.sid}=(.*)")
for wait in 24 * [5]: # tries every 5s for 2min for wait in 24 * [5]: # tries every 5s for 2min
print(f"sending request to {url=}") print(f"sending request to {url=}", flush=True)
r = requests.get(url) r = requests.get(url)
print(f"got response {r.text=}") print(f"got response {r.text=}", flush=True)
if key := regex_string.search(r.text): if key := regex_string.search(r.text):
print(f"got captcha result {key=}") print(f"got captcha result {key=}", flush=True)
return captcha.try_again(key[0]) return captcha.try_again(key[0])
print(f"sleeping {wait} seconds") print(f"sleeping {wait} seconds", flush=True)
time.sleep(wait) time.sleep(wait)
else: else:
key = input("Enter captcha code {0}: ".format(captcha.get_url())).strip() key = input(f"Enter captcha code for {captcha.get_url()}:").strip()
return captcha.try_again(key[0]) return captcha.try_again(key[0])
return False return False