mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-03-09 12:50:23 -05:00
Code Activity

Separate playlist-end and 5000 limit checking

Browse source 
for accuracy and readability
This commit is contained in:
kclauhk 2024-06-27 19:38:26 +08:00
parent 1564c71921
commit ec1d3c97d0
1 changed files with 7 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
yt_dlp/extractor/giphy.py
View file

@ -97,8 +97,8 @@ def _extract_info(self, gif_data, video_id):
'subtitles': subtitles, 'subtitles': subtitles,
} }
def _api_channel_feed(self, channel_id, max_offset=_GIPHY_MAX): def _api_channel_feed(self, channel_id):
offset = 0 count, offset = 0, 0
query_url = f'https://giphy.com/api/v4/channels/{channel_id}/feed/?offset={offset}' query_url = f'https://giphy.com/api/v4/channels/{channel_id}/feed/?offset={offset}'
for _ in itertools.count(1): for _ in itertools.count(1):
search_results = self._download_json(query_url, channel_id, fatal=False, search_results = self._download_json(query_url, channel_id, fatal=False,
@ -110,10 +110,13 @@ def _api_channel_feed(self, channel_id, max_offset=_GIPHY_MAX):
**self._extract_info(video, video['id']), **self._extract_info(video, video['id']),
'webpage_url': video['url'], 'webpage_url': video['url'],
} }
count += len(search_results.get('results'))
if count >= (int_or_none(self.get_param('playlistend')) or (self._GIPHY_MAX + 1)):
return
query_url = url_or_none(search_results.get('next')) or '' query_url = url_or_none(search_results.get('next')) or ''
offset = int(self._search_regex(r'offset=(\d+)', query_url, 'offset', default=0)) offset = int(self._search_regex(r'offset=(\d+)', query_url, 'offset', default=0))
# offset cannot exceed 5000 # offset cannot exceed 5000
if not query_url or offset > min((max_offset or self._GIPHY_MAX) + 1, self._GIPHY_MAX): if not query_url or offset > self._GIPHY_MAX:
return return
@ -242,7 +245,7 @@ def _real_extract(self, url):
if channel_id := self._html_search_regex(r'\{"channelId":\s*([^\}]+)\}', webpage, 'channel_id', default=None): if channel_id := self._html_search_regex(r'\{"channelId":\s*([^\}]+)\}', webpage, 'channel_id', default=None):
uploader_id = self._html_search_meta('twitter:creator', webpage).replace('@', '').lower() uploader_id = self._html_search_meta('twitter:creator', webpage).replace('@', '').lower()
entries = [] entries = []
for i in self._api_channel_feed(channel_id, int_or_none(self.get_param('playlistend'))): for i in self._api_channel_feed(channel_id):
entries.append(i) entries.append(i)
return { return {