diff --git a/downloader.py b/downloader.py
index 8d995faf..1282e0ae 100644
--- a/downloader.py
+++ b/downloader.py
@@ -1852,7 +1852,7 @@ def _tickzoo_extract_video_links_from_html(html: str) -> list:
return video_links
-async def _tickzoo_scrape_tag_playlist(playlist_url: str, scraper, queue, counter, overall_bar):
+async def _tickzoo_scrape_tag_playlist(playlist_url: str, cookies, scraper, queue, counter, overall_bar):
"""Scrape all video URLs across pages from a tickzoo.tv tag or category playlist."""
seen_videos = set()
curr_url = playlist_url
@@ -1860,7 +1860,7 @@ async def _tickzoo_scrape_tag_playlist(playlist_url: str, scraper, queue, counte
while curr_url:
log_info(f"Scraping tag page {page_num}: {curr_url}", indent=1)
- html = await asyncio.to_thread(scraper_core.curl_fetch, curr_url, referer="https://tickzoo.tv/")
+ html = await asyncio.to_thread(scraper_core.curl_fetch, curr_url, cookies=cookies, referer="https://tickzoo.tv/")
if not html:
log_warn(f"Static fetch returned empty/blocked. Trying browser for tag page {page_num}...", indent=2)
page = await scraper.new_page()
@@ -1907,13 +1907,13 @@ async def _tickzoo_scrape_tag_playlist(playlist_url: str, scraper, queue, counte
break
-async def _tickzoo_producer(urls, scraper, queue, counter, overall_bar):
+async def _tickzoo_producer(urls, cookies, scraper, queue, counter, overall_bar):
"""Feed direct video URLs or scrape tag playlists dynamically into the queue."""
for url in urls:
if _tickzoo_is_tag_or_playlist(url):
log_info(f"Scraping tag archive: {url}", indent=1)
try:
- await _tickzoo_scrape_tag_playlist(url, scraper, queue, counter, overall_bar)
+ await _tickzoo_scrape_tag_playlist(url, cookies, scraper, queue, counter, overall_bar)
except Exception as e:
log_error(f"Error scraping tag {url}: {e}", indent=1)
elif _tickzoo_is_video_link(url):
@@ -1928,7 +1928,7 @@ async def _tickzoo_producer(urls, scraper, queue, counter, overall_bar):
await asyncio.sleep(random.uniform(0.3, 0.8))
-async def _tickzoo_worker(queue, scraper, download_dir, skip_existing, overall_bar, bar_pool):
+async def _tickzoo_worker(queue, cookies, scraper, download_dir, skip_existing, overall_bar, bar_pool):
"""Worker processing video URLs sequentially or concurrently with shared browser."""
while True:
url = await queue.get()
@@ -1936,7 +1936,7 @@ async def _tickzoo_worker(queue, scraper, download_dir, skip_existing, overall_b
queue.task_done()
break
try:
- await _tickzoo_process_one(scraper, url, download_dir, skip_existing, overall_bar, bar_pool)
+ await _tickzoo_process_one(scraper, url, cookies, download_dir, skip_existing, overall_bar, bar_pool)
except Exception as e:
log_error(f"Error processing {url}: {e}", indent=1)
overall_bar.update(1)
@@ -1949,15 +1949,18 @@ async def _tickzoo_worker(queue, scraper, download_dir, skip_existing, overall_b
def _tickzoo_extract_embed(html: str) -> str:
"""Pull the video iframe src out of the ", html, re.S | re.I)
+ if not m:
+ # Also check any textarea containing iframe
+ m = re.search(r"]*>(.*?<iframe.*?)", html, re.S | re.I)
if not m:
return ""
- inner = m.group(1)
+ inner = unescape(m.group(1))
m = re.search(r"]*\bsrc\s*=\s*[\"']([^\"']+)[\"']", inner, re.I)
if not m:
m = re.search(r"]*\bsrc\s*=\s*([^\"'>\s]+)", inner, re.I)
if not m:
return ""
- src = unescape(m.group(1).strip())
+ src = m.group(1).strip()
if any(ad in src.lower() for ad in _TICKZOO_AD_HOSTS):
return ""
return src
@@ -2003,13 +2006,13 @@ async def _tickzoo_resolve_media(scraper, embed_url: str, referer_url: str) -> s
"""Resolve the direct media URL from a tickzoo embed host via headless Chrome.
Handles every embed host seen on tickzoo.tv:
- * firestream.to -> POST /api/videos//resolve returns JSON
- {signedVideoUrl: "", ...}
- * hgcloud.to -> HLS master manifest fires as a network response (jwplayer)
- * rubyvidhub.com -> HLS master manifest fires as a network response
- * veev.to -> the mp4 URL lives in