mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-17 18:08:30 +00:00
Code Issues Projects Releases Wiki Activity

[ie/rule34video] Fix extracting duration and view count

Browse Source
This commit is contained in:
gmes78 2025-06-27 11:45:31 +01:00
parent 2f9e5789b7
commit 9d46daeff7
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
yt_dlp/extractor/rule34video.py
View File

@ -93,6 +93,15 @@ def _real_extract(self, url):
uploader = clean_html(uploader_link) uploader = clean_html(uploader_link)
uploader_url = extract_attributes(uploader_link or '').get('href') uploader_url = extract_attributes(uploader_link or '').get('href')
view_count, duration = [None] * 2
for item_info in get_elements_by_class('item_info', webpage):
item_info_text = clean_html(item_info)
if get_element_by_class('custom-eye', item_info) is not None:
precise_view_count = re.search(r'\(([\d,]+)\)', item_info_text)
view_count = parse_count(precise_view_count.group(1) if precise_view_count is not None else item_info_text)
elif get_element_by_class('custom-time', item_info) is not None:
duration = parse_duration(clean_html(item_info))
like_count = None like_count = None
if like_count_text := re.search(r'\(([\d,]+)\)', get_element_by_class('voters count', webpage)): if like_count_text := re.search(r'\(([\d,]+)\)', get_element_by_class('voters count', webpage)):
like_count = parse_count(like_count_text.group(1)) like_count = parse_count(like_count_text.group(1))
@ -113,10 +122,8 @@ def _real_extract(self, url):
'title': self._html_extract_title(webpage), 'title': self._html_extract_title(webpage),
'thumbnail': self._html_search_regex( 'thumbnail': self._html_search_regex(
r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None), r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None),
'duration': parse_duration(self._html_search_regex( 'duration': duration,
r'"icon-clock"></i>\s+<span>((?:\d+:?)+)', webpage, 'duration', default=None)), 'view_count': view_count,
'view_count': int_or_none(self._html_search_regex(
r'"icon-eye"></i>\s+<span>([ \d]+)', webpage, 'views', default='').replace(' ', '')),
'like_count': like_count, 'like_count': like_count,
'comment_count': int_or_none(self._search_regex( 'comment_count': int_or_none(self._search_regex(
r'[^(]+\((\d+)\)', get_element_by_attribute('href', '#tab_comments', webpage), 'comment count', fatal=False)), r'[^(]+\((\d+)\)', get_element_by_attribute('href', '#tab_comments', webpage), 'comment count', fatal=False)),