OpenClaw/extractor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit with extractor project files

Browse Source
This commit is contained in:
OpenClaw Assistant
2026-08-07 12:07:55 +01:00
commit 33851319a4
8 changed files with 27990 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.vscode/settings.json
Vendored Executable
+3
View File
@@ -0,0 +1,3 @@
{
"python-envs.defaultEnvManager": "ms-python.python:system"
}
403_response_cloudscraper.html
Executable
+1
View File
@@ -0,0 +1 @@
<!doctype html><html><head><title>DDoS-Guard</title><meta charset="utf-8"/><meta name="viewport" content="width=device-width,initial-scale=1"/><link rel="stylesheet" href="/.well-known/ddos-guard/js-challenge/index.css"><script defer="defer" src="/.well-known/ddos-guard/js-challenge/view.js"></script><script defer="defer" src="/.well-known/ddos-guard/js-challenge/index.js"></script><script src="https://check.ddos-guard.net/check.js"></script></head><body data-ddg-origin="true" data-ddg-l10n="true"><div class="container"><div class="top"><h1 id="ddg-l10n-title">Checking your browser before accessing <span class="ddg-origin"></span></h1><p id="ddg-l10n-description">Please wait a few seconds. Once this check is complete, the website will open automatically</p><img id="ddg-img-loading" src="" alt="loading"/></div><div class="bottom"><span id="request-info"></span></div></div></body></html>
extract.py
Executable
+366
View File
@@ -0,0 +1,366 @@
import re
import cloudscraper # Changed from requests
from bs4 import BeautifulSoup
import os
import time
import json
from urllib.parse import urlparse, urljoin
class SimPCityExtractor:
def __init__(self, cookies=None):
# Use cloudscraper instead of requests.Session()
self.session = cloudscraper.create_scraper(
browser={
'browser': 'chrome',
'platform': 'windows',
'desktop': True
}
)
# Optional: Add any custom headers (cloudscraper handles most automatically)
self.session.headers.update({
'Accept-Language': 'en-US,en;q=0.9',
})
if cookies:
for name, value in cookies.items():
self.session.cookies.set(name, value, domain='.simpcity.cr')
print("Cookies loaded for authenticated session.")
print(f"Total cookies loaded: {len(cookies)}")
# Test the session
self._test_session()
def _test_session(self):
"""Test if the session is properly authenticated"""
try:
print("\nTesting session authentication...")
test_url = "https://simpcity.cr/"
response = self.session.get(test_url, timeout=30, allow_redirects=True)
print(f"Status Code: {response.status_code}")
print(f"Final URL: {response.url}")
if response.status_code == 403:
print("\n⚠ WARNING: Still receiving 403 Forbidden even with cloudscraper")
print("This suggests:")
print("1. Your cookies are definitely expired/invalid")
print("2. Your IP may be blocked")
print("3. The site requires CAPTCHA solving")
# Check for specific protection
if 'cloudflare' in response.text.lower() or 'cf-ray' in response.headers:
print("→ Cloudflare challenge page detected")
print(" Cloudscraper may need a delay or the challenge is too advanced")
if 'captcha' in response.text.lower():
print("→ CAPTCHA detected - cloudscraper cannot solve CAPTCHAs")
print(" You'll need to use Selenium with CAPTCHA solving service")
# Save response for debugging
with open('403_response_cloudscraper.html', 'w', encoding='utf-8') as f:
f.write(response.text)
print("→ Saved response to '403_response_cloudscraper.html'")
elif response.status_code == 200:
if 'login' in response.url.lower():
print("⚠ Redirected to login page - cookies are invalid or expired")
print(" Export fresh cookies from your browser")
else:
print("✓ Cloudscraper successfully bypassed protection!")
# Check if logged in
if 'logout' in response.text.lower() or 'account' in response.text.lower():
print("✓ Authentication confirmed - you're logged in")
else:
print("⚠ Not logged in - update your cookies")
except Exception as e:
print(f"✗ Error testing session: {e}")
def get_thread_pages(self, base_url, max_pages=50):
"""Discover all pages in a thread by scanning links containing '/page-'."""
pages = []
try:
print(f"\nDiscovering pages for thread: {base_url}")
response = self.session.get(base_url, timeout=30, allow_redirects=True)
print(f"Status: {response.status_code}, URL: {response.url}")
if response.status_code == 403:
print("\n✗ 403 Forbidden - Cannot access thread")
print("Even with cloudscraper, getting 403. This means:")
print("1. Cookies are expired - export fresh ones")
print("2. IP is blocked - try different IP/VPN")
print("3. CAPTCHA required - need Selenium solution")
with open('thread_403_cloudscraper.html', 'w', encoding='utf-8') as f:
f.write(response.text)
print("→ Saved response to 'thread_403_cloudscraper.html'")
return pages
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
page_links = soup.find_all('a', href=True)
page_numbers = set()
for link in page_links:
href = link['href']
match = re.search(r'/page-(\d+)', href)
if match:
page_numbers.add(int(match.group(1)))
if page_numbers:
max_page = min(max(page_numbers), max_pages)
print(f"Found {max_page} pages in thread")
pages.append(base_url)
for page_num in range(2, max_page + 1):
if base_url.endswith('/'):
pages.append(f"{base_url}page-{page_num}")
else:
pages.append(f"{base_url}/page-{page_num}")
else:
print("No pagination found, defaulting to single page")
pages.append(base_url)
except Exception as e:
print(f"Error discovering pages: {e}")
if pages:
return pages
pages.append(base_url)
return pages
def fetch_all_pages_to_file(self, page_urls, output_file):
"""Fetch all thread pages and append them into a single HTML file."""
if not page_urls:
print("No pages to fetch")
return
print(f"\nSaving all pages into: {output_file}")
successful_pages = 0
with open(output_file, 'w', encoding='utf-8') as out_file:
for i, url in enumerate(page_urls, 1):
print(f"\nFetching page {i}/{len(page_urls)}: {url}")
try:
response = self.session.get(url, timeout=30, allow_redirects=True)
print(f" Status: {response.status_code}")
if response.status_code == 403:
print(f" ✗ 403 Forbidden on page {i}")
continue
response.raise_for_status()
if 'login' in response.url.lower():
print(" ✗ Redirected to login page")
continue
out_file.write(f"\n<!-- PAGE {i}: {url} -->\n")
out_file.write(response.text + "\n\n")
successful_pages += 1
print(f" ✓ Successfully saved page {i}")
except Exception as e:
print(f" ✗ Error fetching page {i}: {e}")
# Be polite with delays
if i < len(page_urls):
time.sleep(2)
print(f"\n✓ Successfully saved {successful_pages}/{len(page_urls)} pages")
def resolve_turbovid(self, url):
"""Resolve Turbovid URLs using their sign API endpoint."""
try:
match = re.search(r'/(v|d|embed)/([a-zA-Z0-9]+)', url)
if not match:
print(f" ✗ Could not extract video ID from: {url}")
return None
video_id = match.group(2)
print(f" Resolving Turbovid ID: {video_id}")
embed_url = f"https://turbo.cr/embed/{video_id}"
sign_urls = [
f"https://turbo.cr/api/sign?v={video_id}",
f"https://turbo.cr/sign?v={video_id}",
]
for sign_url in sign_urls:
try:
response = self.session.get(
sign_url,
headers={'Referer': embed_url},
timeout=30
)
if response.status_code == 200:
data = response.json()
if data.get('success') and data.get('url'):
signed_url = data['url']
original_name = data.get('original_filename')
if original_name and 'fn=' not in signed_url:
delimiter = '&' if '?' in signed_url else '?'
signed_url += f"{delimiter}fn={original_name}"
print(f" ✓ Resolved to: {signed_url[:80]}...")
return signed_url
except Exception as e:
continue
try:
response = self.session.get(embed_url, headers={'Referer': embed_url}, timeout=30)
soup = BeautifulSoup(response.text, 'html.parser')
source_tag = soup.find('source', src=True)
if source_tag:
return source_tag['src']
video_tag = soup.find('video', src=True)
if video_tag:
return video_tag['src']
except Exception:
pass
return None
except Exception as e:
print(f" ✗ Error resolving Turbovid: {e}")
return None
# Rest of the functions remain the same...
def extract_links(file_path, resolve_turbovid=False, extractor=None):
"""Extract links from an HTML file using regex."""
if not os.path.exists(file_path):
print(f"File not found: {file_path}")
return []
with open(file_path, 'r', encoding='utf-8') as f:
html = f.read()
if len(html) < 1000 and '403' in html:
print("⚠ Warning: HTML file appears to contain 403 error page")
return []
patterns = [
r'https?://\S*bunkr\.\S*',
r'https?://[a-zA-Z0-9\-]+\.jpg5\.su/images3/[^\s"\'<>]+?\.md\.jpg',
r'https?://jpg6\.su/img/[a-zA-Z0-9]+',
r'https?://jpg6\.su/a/[^\s"\'<>]+',
r'https?://saint2\.cr/embed/[a-zA-Z0-9]+',
r'https?://(?:www\.)?redgifs\.com/watch/[a-zA-Z0-9]+',
r'//redgifs\.com/ifr/[a-zA-Z0-9]+',
r'https?://gofile\.io/d/[a-zA-Z0-9]+',
r'https?://pixeldrain\.com/u/[a-zA-Z0-9]+',
r'https?://cyberdrop\.me/a/[a-zA-Z0-9]+',
r'https?://cyberdrop\.cr/f/[a-zA-Z0-9]+',
r'https?://(?:[\w-]+\.)?turbo(?:vid)?\.cr/(?:v|d|embed)/[a-zA-Z0-9]+',
r'https?://goonbox\.cr/img/[a-zA-Z0-9]+',
r'https?://goonbox\.ce/a/[^\s"\'<>]+',
]
clean_links = []
for pattern in patterns:
matches = re.findall(pattern, html)
for match in matches:
clean_link = match.strip().rstrip('"\'<>')
clean_links.append(clean_link)
unique_links = list(set(clean_links))
print(f"\nFound {len(unique_links)} unique links total")
if resolve_turbovid and extractor:
print("\n--- Resolving Turbovid Links ---")
resolved_links = []
turbovid_count = 0
failed_count = 0
for link in unique_links:
if 'turbo' in link.lower() and '.cr' in link.lower():
turbovid_count += 1
print(f"\nProcessing Turbovid link {turbovid_count}: {link}")
resolved = extractor.resolve_turbovid(link)
if resolved:
resolved_links.append(resolved)
else:
failed_count += 1
time.sleep(1)
else:
resolved_links.append(link)
print(f"\nResolved {turbovid_count - failed_count}/{turbovid_count} Turbovid links")
if failed_count > 0:
print(f"Failed: {failed_count} Turbovid link(s)")
return resolved_links
return unique_links
def save_links_to_file(links, output_file):
if not links:
print("No links found to save.")
return
existing = set()
if os.path.exists(output_file):
with open(output_file, 'r', encoding='utf-8') as f:
existing = set(line.strip() for line in f if line.strip())
new_links = [l for l in links if l not in existing]
if not new_links:
print("No new unique links found.")
return
with open(output_file, 'a', encoding='utf-8') as f:
for link in new_links:
f.write(link + "\n")
print(f"✓ Saved {len(new_links)} new links to {output_file}")
if __name__ == "__main__":
print("="*70)
print("SimPCity Link Extractor - Cloudscraper Version")
print("="*70)
print("\nMake sure you have cloudscraper installed:")
print(" pip install cloudscraper\n")
base_thread_url = "https://simpcity.cr/threads/haileyybrown.50455/"
output_html = "page_source.html"
output_links = "links.txt"
# CRITICAL: Export FRESH cookies from your browser while logged in
cookies = {
"__ddg1_": "ztu3bAWXt1yNTQLx4anD",
"__ddg2_": "XITPIP1OKNx5qhiT",
"__ddg8_": "oWldvDW5w2JAjymf",
"__ddg9_": "217.138.213.52",
"__ddg10_": "1781612477",
"__ddgid_": "yhSli2A9nG5Xkwcu",
"__ddgmark_": "pVXsbrKqDemwPHiu",
"oMased": "b4",
"oMasid": "9e19ba410603e03b1286baca7c2917ef56b9c760415db5e2b9574c87eb092e7e",
"ogaddgmetaprof_csrf": "",
"yMziCv8BrCZz1o7_csrf": "vGZEMX5-P-XSKuG_",
"yMziCv8BrCZz1o7_session": "upTVlbK2kspfKlRGyD74rOh_PacNF7DI",
"yMziCv8BrCZz1o7_user": "3944332%2Cr8xH2AcnE_hg0kkeNSSsi3luzSkW6odfKX21CHdk",
"yMziCv8BrCZz1o7_dbWriteForced": "1781612424"
}
extractor = SimPCityExtractor(cookies=cookies)
pages = extractor.get_thread_pages(base_thread_url)
if pages:
extractor.fetch_all_pages_to_file(pages, output_html)
links = extract_links(output_html, resolve_turbovid=True, extractor=extractor)
save_links_to_file(links, output_links)
print("\n" + "="*70)
print("Process completed!")
f95extract.py
Executable
+370
View File
@@ -0,0 +1,370 @@
import re
import cloudscraper # Changed from requests
from bs4 import BeautifulSoup
import os
import time
import json
from urllib.parse import urlparse, urljoin
class SimPCityExtractor:
def __init__(self, cookies=None):
# Use cloudscraper instead of requests.Session()
self.session = cloudscraper.create_scraper(
browser={
'browser': 'chrome',
'platform': 'windows',
'desktop': True
}
)
# Optional: Add any custom headers (cloudscraper handles most automatically)
self.session.headers.update({
'Accept-Language': 'en-US,en;q=0.9',
})
if cookies:
for name, value in cookies.items():
self.session.cookies.set(name, value, domain='.f95zone.to')
print("Cookies loaded for authenticated session.")
print(f"Total cookies loaded: {len(cookies)}")
# Test the session
self._test_session()
def _test_session(self):
"""Test if the session is properly authenticated"""
try:
print("\nTesting session authentication...")
test_url = "https://f95zone.to/"
response = self.session.get(test_url, timeout=30, allow_redirects=True)
print(f"Status Code: {response.status_code}")
print(f"Final URL: {response.url}")
if response.status_code == 403:
print("\n⚠ WARNING: Still receiving 403 Forbidden even with cloudscraper")
print("This suggests:")
print("1. Your cookies are definitely expired/invalid")
print("2. Your IP may be blocked")
print("3. The site requires CAPTCHA solving")
# Check for specific protection
if 'cloudflare' in response.text.lower() or 'cf-ray' in response.headers:
print("→ Cloudflare challenge page detected")
print(" Cloudscraper may need a delay or the challenge is too advanced")
if 'captcha' in response.text.lower():
print("→ CAPTCHA detected - cloudscraper cannot solve CAPTCHAs")
print(" You'll need to use Selenium with CAPTCHA solving service")
# Save response for debugging
with open('403_response_cloudscraper.html', 'w', encoding='utf-8') as f:
f.write(response.text)
print("→ Saved response to '403_response_cloudscraper.html'")
elif response.status_code == 200:
if 'login' in response.url.lower():
print("⚠ Redirected to login page - cookies are invalid or expired")
print(" Export fresh cookies from your browser")
else:
print("✓ Cloudscraper successfully bypassed protection!")
# Check if logged in
if 'logout' in response.text.lower() or 'account' in response.text.lower():
print("✓ Authentication confirmed - you're logged in")
else:
print("⚠ Not logged in - update your cookies")
except Exception as e:
print(f"✗ Error testing session: {e}")
def get_thread_pages(self, base_url, max_pages=50):
"""Discover all pages in a thread by scanning links containing '/page-'."""
pages = []
try:
print(f"\nDiscovering pages for thread: {base_url}")
response = self.session.get(base_url, timeout=30, allow_redirects=True)
print(f"Status: {response.status_code}, URL: {response.url}")
if response.status_code == 403:
print("\n✗ 403 Forbidden - Cannot access thread")
print("Even with cloudscraper, getting 403. This means:")
print("1. Cookies are expired - export fresh ones")
print("2. IP is blocked - try different IP/VPN")
print("3. CAPTCHA required - need Selenium solution")
with open('thread_403_cloudscraper.html', 'w', encoding='utf-8') as f:
f.write(response.text)
print("→ Saved response to 'thread_403_cloudscraper.html'")
return pages
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
page_links = soup.find_all('a', href=True)
page_numbers = set()
for link in page_links:
href = link['href']
match = re.search(r'/page-(\d+)', href)
if match:
page_numbers.add(int(match.group(1)))
if page_numbers:
max_page = min(max(page_numbers), max_pages)
print(f"Found {max_page} pages in thread")
pages.append(base_url)
for page_num in range(2, max_page + 1):
if base_url.endswith('/'):
pages.append(f"{base_url}page-{page_num}")
else:
pages.append(f"{base_url}/page-{page_num}")
else:
print("No pagination found, defaulting to single page")
pages.append(base_url)
except Exception as e:
print(f"Error discovering pages: {e}")
if pages:
return pages
pages.append(base_url)
return pages
def fetch_all_pages_to_file(self, page_urls, output_file):
"""Fetch all thread pages and append them into a single HTML file."""
if not page_urls:
print("No pages to fetch")
return
print(f"\nSaving all pages into: {output_file}")
successful_pages = 0
with open(output_file, 'w', encoding='utf-8') as out_file:
for i, url in enumerate(page_urls, 1):
print(f"\nFetching page {i}/{len(page_urls)}: {url}")
try:
response = self.session.get(url, timeout=30, allow_redirects=True)
print(f" Status: {response.status_code}")
if response.status_code == 403:
print(f" ✗ 403 Forbidden on page {i}")
continue
response.raise_for_status()
if 'login' in response.url.lower():
print(" ✗ Redirected to login page")
continue
out_file.write(f"\n<!-- PAGE {i}: {url} -->\n")
out_file.write(response.text + "\n\n")
successful_pages += 1
print(f" ✓ Successfully saved page {i}")
except Exception as e:
print(f" ✗ Error fetching page {i}: {e}")
# Be polite with delays
if i < len(page_urls):
time.sleep(2)
print(f"\n✓ Successfully saved {successful_pages}/{len(page_urls)} pages")
def resolve_turbovid(self, url):
"""Resolve Turbovid URLs using their sign API endpoint."""
try:
match = re.search(r'/(v|d|embed)/([a-zA-Z0-9]+)', url)
if not match:
print(f" ✗ Could not extract video ID from: {url}")
return None
video_id = match.group(2)
print(f" Resolving Turbovid ID: {video_id}")
embed_url = f"https://turbo.cr/embed/{video_id}"
sign_urls = [
f"https://turbo.cr/api/sign?v={video_id}",
f"https://turbo.cr/sign?v={video_id}",
]
for sign_url in sign_urls:
try:
response = self.session.get(
sign_url,
headers={'Referer': embed_url},
timeout=30
)
if response.status_code == 200:
data = response.json()
if data.get('success') and data.get('url'):
signed_url = data['url']
original_name = data.get('original_filename')
if original_name and 'fn=' not in signed_url:
delimiter = '&' if '?' in signed_url else '?'
signed_url += f"{delimiter}fn={original_name}"
print(f" ✓ Resolved to: {signed_url[:80]}...")
return signed_url
except Exception as e:
continue
try:
response = self.session.get(embed_url, headers={'Referer': embed_url}, timeout=30)
soup = BeautifulSoup(response.text, 'html.parser')
source_tag = soup.find('source', src=True)
if source_tag:
return source_tag['src']
video_tag = soup.find('video', src=True)
if video_tag:
return video_tag['src']
except Exception:
pass
return None
except Exception as e:
print(f" ✗ Error resolving Turbovid: {e}")
return None
# Rest of the functions remain the same...
def extract_links(file_path, resolve_turbovid=False, extractor=None):
"""Extract links from an HTML file using regex."""
if not os.path.exists(file_path):
print(f"File not found: {file_path}")
return []
with open(file_path, 'r', encoding='utf-8') as f:
html = f.read()
if len(html) < 1000 and '403' in html:
print("⚠ Warning: HTML file appears to contain 403 error page")
return []
patterns = [
r'https?://\S*bunkr\.\S*',
r'https?://[a-zA-Z0-9\-]+\.jpg5\.su/images3/[^\s"\'<>]+?\.md\.jpg',
r'https?://jpg6\.su/img/[a-zA-Z0-9]+',
r'https?://jpg6\.su/a/[^\s"\'<>]+',
r'https?://saint2\.cr/embed/[a-zA-Z0-9]+',
r'https?://(?:www\.)?redgifs\.com/watch/[a-zA-Z0-9]+',
r'//redgifs\.com/ifr/[a-zA-Z0-9]+',
r'https?://gofile\.io/d/[a-zA-Z0-9]+',
r'https?://pixeldrain\.com/u/[a-zA-Z0-9]+',
r'https?://cyberdrop\.me/a/[a-zA-Z0-9]+',
r'https?://cyberdrop\.cr/f/[a-zA-Z0-9]+',
r'https?://(?:[\w-]+\.)?turbo(?:vid)?\.cr/(?:v|d|embed)/[a-zA-Z0-9]+',
r'https?://goonbox\.cr/img/[a-zA-Z0-9]+',
r'https?://goonbox\.ce/a/[^\s"\'<>]+',
r'https?://attachments\.f95zone\.to(?:/[a-zA-Z0-9]+)+'
r'https?://mega\.nz/file/[a-zA-Z0-9]+',
r'https?://drive\.google\.come/file/d/[a-zA-Z0-9]+',
r'https?://f95zone\.to/attachments/[a-zA-Z0-9]+',
]
clean_links = []
for pattern in patterns:
matches = re.findall(pattern, html)
for match in matches:
clean_link = match.strip().rstrip('"\'<>')
clean_links.append(clean_link)
unique_links = list(set(clean_links))
print(f"\nFound {len(unique_links)} unique links total")
if resolve_turbovid and extractor:
print("\n--- Resolving Turbovid Links ---")
resolved_links = []
turbovid_count = 0
failed_count = 0
for link in unique_links:
if 'turbo' in link.lower() and '.cr' in link.lower():
turbovid_count += 1
print(f"\nProcessing Turbovid link {turbovid_count}: {link}")
resolved = extractor.resolve_turbovid(link)
if resolved:
resolved_links.append(resolved)
else:
failed_count += 1
time.sleep(1)
else:
resolved_links.append(link)
print(f"\nResolved {turbovid_count - failed_count}/{turbovid_count} Turbovid links")
if failed_count > 0:
print(f"Failed: {failed_count} Turbovid link(s)")
return resolved_links
return unique_links
def save_links_to_file(links, output_file):
if not links:
print("No links found to save.")
return
existing = set()
if os.path.exists(output_file):
with open(output_file, 'r', encoding='utf-8') as f:
existing = set(line.strip() for line in f if line.strip())
new_links = [l for l in links if l not in existing]
if not new_links:
print("No new unique links found.")
return
with open(output_file, 'a', encoding='utf-8') as f:
for link in new_links:
f.write(link + "\n")
print(f"✓ Saved {len(new_links)} new links to {output_file}")
if __name__ == "__main__":
print("="*70)
print("SimPCity Link Extractor - Cloudscraper Version")
print("="*70)
print("\nMake sure you have cloudscraper installed:")
print(" pip install cloudscraper\n")
base_thread_url = "https://f95zone.to/threads/qiandai-collection-2026-01-04-qiandaiyiyu-qiandai.246056/"
output_html = "page_source.html"
output_links = "links.txt"
# CRITICAL: Export FRESH cookies from your browser while logged in
cookies = {
"__ddg1_": "ztu3bAWXt1yNTQLx4anD",
"__ddg2_": "XITPIP1OKNx5qhiT",
"__ddg8_": "oWldvDW5w2JAjymf",
"__ddg9_": "217.138.213.52",
"__ddg10_": "1781612477",
"__ddgid_": "yhSli2A9nG5Xkwcu",
"__ddgmark_": "pVXsbrKqDemwPHiu",
"oMased": "b4",
"oMasid": "9e19ba410603e03b1286baca7c2917ef56b9c760415db5e2b9574c87eb092e7e",
"ogaddgmetaprof_csrf": "",
"yMziCv8BrCZz1o7_csrf": "vGZEMX5-P-XSKuG_",
"yMziCv8BrCZz1o7_session": "upTVlbK2kspfKlRGyD74rOh_PacNF7DI",
"yMziCv8BrCZz1o7_user": "3944332%2Cr8xH2AcnE_hg0kkeNSSsi3luzSkW6odfKX21CHdk",
"yMziCv8BrCZz1o7_dbWriteForced": "1781612424"
}
extractor = SimPCityExtractor(cookies=cookies)
pages = extractor.get_thread_pages(base_thread_url)
if pages:
extractor.fetch_all_pages_to_file(pages, output_html)
links = extract_links(output_html, resolve_turbovid=True, extractor=extractor)
save_links_to_file(links, output_links)
print("\n" + "="*70)
print("Process completed!")
links.txt
Executable
+217
View File
@@ -0,0 +1,217 @@
https://goonbox.cr/img/FAcymt
https://goonbox.cr/img/YMATKPH
https://goonbox.cr/img/YSEp9vW
https://goonbox.cr/img/Clyat6
https://goonbox.cr/img/YMAixVf
https://goonbox.cr/img/YMATvUy
https://goonbox.cr/img/tnAGtou
//redgifs.com/ifr/illegalidioticseaslug
https://goonbox.cr/img/tnABhwu
https://goonbox.cr/img/CMGfeo
https://goonbox.cr/img/CMGrO5
https://goonbox.cr/img/YMATFO5
https://goonbox.cr/img/tnABjJI
https://goonbox.cr/img/YMATHpK
https://goonbox.cr/img/FAccxh
https://goonbox.cr/img/ClsAgK
https://goonbox.cr/img/Yd96wX5
https://goonbox.cr/img/jCydec
https://dl100.turbocdn.st/turbo/data/dfdab4c0482e06bbf97a4f031f794fcd.mp4?exp=1784628166&token=972212f7a0a53ec1f5a2a1be5ff87f5b1db74547aa8c6d49e72bd86488bff1c3&fn=dfdab4c0482e06bbf97a4f031f794fcd.mp4
https://goonbox.cr/img/ClsdAw
https://goonbox.cr/img/aZ46s5u
https://goonbox.cr/img/Yd96haS
https://goonbox.cr/img/YUYZ1Vm
//redgifs.com/ifr/tiredrowdystagbeetle
https://goonbox.cr/img/wRJ60P
https://dl100.turbocdn.st/turbo/data/9085b3cbd1d9abdd6fa0701aed5ad613.m4v?exp=1784628167&token=c255685c4c91513b17bdf29806c8b56f979abf236880d4641d96e49be3b92a9c&fn=9085b3cbd1d9abdd6fa0701aed5ad613.m4v
https://goonbox.cr/img/YUYZnH7
https://goonbox.cr/img/YSOeM9A
https://goonbox.cr/img/YMATe0e
https://goonbox.cr/img/atlKUNp
https://goonbox.cr/img/YSOeO1u
https://goonbox.cr/img/FAcuQW
https://goonbox.cr/img/aZ46yxI
https://dl100.turbocdn.st/turbo/data/b466c20357814a6c65bfdd6fe72dcc5a.mp4?exp=1784628171&token=b2024b1cc9114b5c268406da069bef4250bc0b41ef1afd408e383986dfed8d7c&fn=b466c20357814a6c65bfdd6fe72dcc5a.mp4
https://dl100.turbocdn.st/turbo/data/Ni3GRf1ZIoc.mp4?exp=1784628172&token=9a874d136b438328aefd44e64668276c72e813121bea38cc95642d98e5ee92d8&fn=Ni3GRf1ZIoc.mp4
https://goonbox.cr/img/tnArRV1
https://goonbox.cr/img/Yd96jXW
https://goonbox.cr/img/Cly9Fe
https://goonbox.cr/img/Clswwd
https://goonbox.cr/img/YMATELa
//redgifs.com/ifr/standardfewvelvetcrab
https://goonbox.cr/img/Yd96Uy9
https://goonbox.cr/img/MTQUsy
https://goonbox.cr/img/ClyLBD
//redgifs.com/ifr/hatefulfreeswift
https://dl100.turbocdn.st/turbo/data/uLmFi1iE7uEvL.mp4?exp=1784628173&token=3f0918cac7853339ef8014d0c34849785c4582166ad584ac31b7ae8b19e28c1d&fn=BlackPerkyAsianelephant.mp4
https://goonbox.cr/img/wRJtR5
https://goonbox.cr/img/YUP3Jeu
https://goonbox.cr/img/YLLS30h
https://goonbox.cr/img/Yd96d4p
https://goonbox.cr/img/CMV3vh
https://goonbox.cr/img/tnArje6
https://goonbox.cr/img/Yd96OZE
https://goonbox.cr/img/wRDxLe
https://goonbox.cr/img/CMGuci
https://bunkr.cr/a/hojeA11a</a></div>Might
https://goonbox.cr/img/FAsYHn
https://goonbox.cr/img/Cls1Zg
https://goonbox.cr/img/ClsOI7
//redgifs.com/ifr/bossyfrankcurassow
https://goonbox.cr/img/Y0lt6Vh
https://goonbox.cr/img/YUfKbMh
https://goonbox.cr/img/wRDJun
https://goonbox.cr/img/aZ462Go
//redgifs.com/ifr/ellipticalstripedgavial
https://goonbox.cr/img/Cly6Mg
https://goonbox.cr/img/Cls8y6
https://goonbox.cr/img/YUfKAiG
https://goonbox.cr/img/wRJYp9
https://goonbox.cr/img/ClshXh
https://goonbox.cr/img/FAcf3D
https://goonbox.cr/img/YMATRpG
https://dl100.turbocdn.st/turbo/data/HdoYYJY0th2XX.mp4?exp=1784628176&token=a4ed4ede09d01cf863519ce2766160220e247663d0b021faa8e2db420276e104&fn=PrivateHoarseKagu.mp4
https://goonbox.cr/img/Clyvic
https://dl100.turbocdn.st/turbo/data/4f90c3c90b67165e5d56c96a050d5f6a.mp4?exp=1784628177&token=355b48a76bc1116a4b166ade2b6c1c4642e01a76ab1a6ead63dc30000b2a7412&fn=4f90c3c90b67165e5d56c96a050d5f6a.mp4
https://goonbox.cr/img/Clssbe
https://www.redgifs.com/watch/putridfloralwhitebaldeagle
//redgifs.com/ifr/wronghopefulsnake
https://goonbox.cr/img/ClsxnA
https://goonbox.cr/img/YUYZhlg
https://bunkr.cr/v/9MKkiy7cwee8S</a></div></div
https://goonbox.cr/img/ClyKTE
https://goonbox.cr/img/FAsNVy
https://goonbox.cr/img/tnArY3W
https://goonbox.cr/img/ClsQZp
https://goonbox.cr/img/MTQka9
//redgifs.com/ifr/instructivelimppanther
https://goonbox.cr/img/Clyt2h
https://goonbox.cr/img/Cls2JE
https://goonbox.cr/img/ClsVBa
https://dl100.turbocdn.st/turbo/data/p6cSN41GTPk3g.mp4?exp=1784628179&token=9913297db5aa531cfb3dca67779ff52e09a4d1a5abcf6477133c65bae82a972c&fn=NearWateryVelvetworm.mp4
https://www.redgifs.com/watch/smughungrynorthernhairynosedwombat
https://bunkr.cr/v/9MKkiy7cwee8S
https://goonbox.cr/img/FAcl9S
https://goonbox.cr/img/YMAT37n
https://goonbox.cr/img/YUP3oRI
https://dl100.turbocdn.st/turbo/data/itHlE264iGCgy.mp4?exp=1784628181&token=60a4cbd50ecc6afbb7be41fd9bb3be58b749c8d99a32dbf67112359ebb71ca8b&fn=PlaintiveClutteredKentrosaurus.mp4
https://goonbox.cr/img/YUfKpo6
//redgifs.com/ifr/navybluereflectinghumpbackwhale
//redgifs.com/ifr/uprightinstructivesidewinder
https://dl100.turbocdn.st/turbo/data/2Rkf576ZJ5eNj.mp4?exp=1784628182&token=8e9dac702d9fbdfbcb1bbbbc0799ad10970f302f688bd13fb073900590f3407b&fn=EnchantedOlivedrabSnowmonkey.mp4
https://goonbox.cr/img/ClsICm
https://goonbox.cr/img/FAcAVm
https://goonbox.cr/img/ClsnDc
https://bunkr.cr/a/xDIsT70G</a
https://goonbox.cr/img/YMAT9d6
https://goonbox.cr/img/YMATZRP
//redgifs.com/ifr/filthyagreeableeyelashpitviper
https://dl100.turbocdn.st/turbo/data/216c266eed23b3f8964e9490f3dc9f18.m4v?exp=1784628183&token=f539b9e931b5653c9ca5523174003c43242a9979c8c6841bf18159cce6d42a55&fn=216c266eed23b3f8964e9490f3dc9f18.m4v
https://goonbox.cr/img/ClsX6A
https://goonbox.cr/img/YUP3xcH
https://goonbox.cr/img/YSOekmG
//redgifs.com/ifr/dishonestbasicgreatdane
https://goonbox.cr/img/ClyT2f
https://goonbox.cr/img/wRJ3cK
https://goonbox.cr/img/ClsBCy
https://goonbox.cr/img/YSOewUh
https://www.redgifs.com/watch/deadlivelyhorsechestnutleafminer
https://goonbox.cr/img/Clsgj1
https://goonbox.cr/img/aZ46pl1
https://goonbox.cr/img/aZ46AH6
https://goonbox.cr/img/aKv3wkg
https://goonbox.cr/img/FAsaOe
https://goonbox.cr/img/CMVad6
https://goonbox.cr/img/YMATYed
https://bunkr.cr/a/hojeA11a
https://dl100.turbocdn.st/turbo/data/a9FjxpoLa64WK.mp4?exp=1784628184&token=73ff88e4f8b1286a804f2c6e8041880be97ade4fbf684f1c5746ae7b79ce1d94&fn=WatchfulFirmChinesecrocodilelizard.mp4
https://bunkr.cr/a/4IpIC7ft
https://goonbox.cr/img/YMATaRE
https://goonbox.cr/img/YUfKuEc
https://goonbox.cr/img/CMGJ0I
https://goonbox.cr/img/gyyowd
https://goonbox.cr/img/YMATNQp
https://goonbox.cr/img/tnAp3AA
https://goonbox.cr/img/YUPeNP6
https://goonbox.cr/img/FAcJmd
https://goonbox.cr/img/YSOedVI
https://goonbox.cr/img/YUP3zpi
https://goonbox.cr/img/YMAioOW
https://goonbox.cr/img/YMAT6u9
https://goonbox.cr/img/atlKk2e
https://goonbox.cr/img/Yd96kNa
https://bunkr.cr/a/jVQHrc1j
https://bunkr.cr/a/jVQHrc1j</a></div>I
https://goonbox.cr/img/wRJNva
https://dl100.turbocdn.st/turbo/data/Xy6gIjCcs6y.mp4?exp=1784628186&token=f7b20207f25671f9952f6120e92afb4e459fdfef516c5fb8cd3c763dd52e2a51&fn=Xy6gIjCcs6y.mp4
https://goonbox.cr/img/aZ46Q3P
https://goonbox.cr/img/Clsjwt
https://goonbox.cr/img/tnArPVD
https://goonbox.cr/img/YSOenlP
https://goonbox.cr/img/YSOeIeH
https://goonbox.cr/img/YLLSYR1
https://goonbox.cr/img/YLLSt7G
https://dl100.turbocdn.st/turbo/data/b8788e03ed39b15cc722c802e6aaba44.mp4?exp=1784628187&token=ec512b4482e8d4d0b381183485b54aa84d04b54f998eed305b6be990896af4ce&fn=b8788e03ed39b15cc722c802e6aaba44.mp4
https://goonbox.cr/img/YUP3lHo
https://goonbox.cr/img/aKv32D7
https://goonbox.cr/img/FAcGlg
https://goonbox.cr/img/tnAGN5i
https://dl100.turbocdn.st/turbo/data/byYinLjWWZI.mp4?exp=1784628188&token=9760ec8cca4534a122083cccde9496e9c58213d23ffa1a113fce6902d0b6f872&fn=byYinLjWWZI.mp4
https://goonbox.cr/img/ClskXf
https://goonbox.cr/img/ClsRaG
https://goonbox.cr/img/YUfKfft
https://goonbox.cr/img/aZ46GmH
https://dl100.turbocdn.st/turbo/data/P1HJbAxIswHhs.mp4?exp=1784628190&token=bb2bbbf6912da64d7387142136f885914d8648d0c0c98a26fc9a7f40c1b6bd76&fn=ExtrovertedFaintWhitepelican.mp4
https://goonbox.cr/img/FAcBSc
https://goonbox.cr/img/YUP3uOP
https://goonbox.cr/img/Cls0AH
https://goonbox.cr/img/YUYZd3D
https://goonbox.cr/img/tnArz7o
https://bunkr.cr/a/xDIsT70G
https://goonbox.cr/img/ClsMjD
https://goonbox.cr/img/Yd962wK
https://goonbox.cr/img/ClsSyS
https://goonbox.cr/img/wRDDUp
https://goonbox.cr/img/atlKPgn
https://goonbox.cr/img/Clyi8W
https://goonbox.cr/img/YSOe1Hi
https://goonbox.cr/img/YUfKV21
https://goonbox.cr/img/YMAT00I
https://www.redgifs.com/watch/pungentdamagedmorpho
https://goonbox.cr/img/YUPea01
https://goonbox.cr/img/wRJCPi
https://goonbox.cr/img/YMATWeo
https://goonbox.cr/img/FAcpH7
//redgifs.com/ifr/idlewrathfulcornsnake
https://goonbox.cr/img/YLLS7eA
https://goonbox.cr/img/CMGxuA
https://goonbox.cr/img/Yd96MCe
https://bunkr.cr/a/4IpIC7ft</a></div></div
https://goonbox.cr/img/FAcxlp
https://goonbox.cr/img/YMAiJHS
https://goonbox.cr/img/ClsPNW
https://goonbox.cr/img/ClszIu
https://goonbox.cr/img/YSOeP76
https://goonbox.cr/img/ClyFEw
https://dl100.turbocdn.st/turbo/data/6ece23a7e5625b23c22ed7f8296af6f6.mp4?exp=1784628194&token=ddf17a362530aea08e48516a35179b1cc259e186139845d6c4bd9e477204db23&fn=6ece23a7e5625b23c22ed7f8296af6f6.mp4
https://dl100.turbocdn.st/turbo/data/13264d3bf41f3f952c2eb4f207e4b55e.m4v?exp=1784628195&token=b9aabe3ee04c0d9b36f3ee7233a8be23bae88d6b19503e688fd21fd9a2e96e20&fn=13264d3bf41f3f952c2eb4f207e4b55e.m4v
https://goonbox.cr/img/wRJv7o
https://goonbox.cr/img/YUPeY7A
https://goonbox.cr/img/tnAri5o
https://goonbox.cr/img/YUfKzqg
https://dl100.turbocdn.st/turbo/data/19aa66817df66c1502bed3fa230aab0e.mp4?exp=1784628196&token=090b8fa778f87a32352de4058098c073638e9a4d966bead53bf6e16954f9f434&fn=19aa66817df66c1502bed3fa230aab0e.mp4
https://www.redgifs.com/watch/euphoricsandybrownbandicoot
//redgifs.com/ifr/lostaptbluebottlejellyfish
https://goonbox.cr/img/FAcr1w
https://goonbox.cr/img/tnArvSn
https://goonbox.cr/img/tnArpOy
https://dl100.turbocdn.st/turbo/data/7d0b3c6c30a5a2a365b071f82b33ad5b.mp4?exp=1784628197&token=142189fa6e731c88bc1dbea395296b479f12c772ffd87ce8d5e29b4bdedcde81&fn=7d0b3c6c30a5a2a365b071f82b33ad5b.mp4
https://goonbox.cr/img/aZ46b1G
https://dl100.turbocdn.st/turbo/data/fa23b69e3cfe943e733e29a28f6ae79c.mp4?exp=1784628198&token=e9f7fbb46989d7aa87db6ab32da007dcd3e5967ce2315561e973353331fd8822&fn=fa23b69e3cfe943e733e29a28f6ae79c.mp4
https://goonbox.cr/img/FAcoUE
https://goonbox.cr/img/YUYZq1w
https://goonbox.cr/img/ClsfJP
https://goonbox.cr/img/wRJ7Oy
https://goonbox.cr/img/YUYZ49S
https://goonbox.cr/img/ClscIn
//redgifs.com/ifr/hollowfemininechick
page.txt
Executable
View File
page_source.html
Executable
+25745
View File
File diff suppressed because one or more lines are too long
thread_403_cloudscraper.html
Executable
+1288
View File
File diff suppressed because it is too large Load Diff