mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[crunchyroll] Fix thumbnail (#650)

Browse Source 
Authored by: funniray
This commit is contained in:
funniray 2021-08-09 22:39:20 +01:00 committed by GitHub
parent 246fb276e0
commit 245d43cacf
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/crunchyroll.py
View File

@ -29,6 +29,7 @@
merge_dicts, merge_dicts,
remove_end, remove_end,
sanitized_Request, sanitized_Request,
try_get,
urlencode_postdata, urlencode_postdata,
xpath_text, xpath_text,
) )
@ -458,6 +459,18 @@ def _real_extract(self, url):
video_description = (self._parse_json(self._html_search_regex( video_description = (self._parse_json(self._html_search_regex(
r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id, r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
webpage, 'description', default='{}'), video_id) or media_metadata).get('description') webpage, 'description', default='{}'), video_id) or media_metadata).get('description')
thumbnails = []
thumbnail_url = (self._parse_json(self._html_search_regex(
r'<script type="application\/ld\+json">\n\s*(.+?)<\/script>',
webpage, 'thumbnail_url', default='{}'), video_id)).get('image')
if thumbnail_url:
thumbnails.append({
'url': thumbnail_url,
'width': 1920,
'height': 1080
})
if video_description: if video_description:
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
@ -592,21 +605,25 @@ def _real_extract(self, url):
r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d', r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
webpage, 'series', fatal=False) webpage, 'series', fatal=False)
season = episode = episode_number = duration = thumbnail = None season = episode = episode_number = duration = None
if isinstance(metadata, compat_etree_Element): if isinstance(metadata, compat_etree_Element):
season = xpath_text(metadata, 'series_title') season = xpath_text(metadata, 'series_title')
episode = xpath_text(metadata, 'episode_title') episode = xpath_text(metadata, 'episode_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number')) episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
duration = float_or_none(media_metadata.get('duration'), 1000) duration = float_or_none(media_metadata.get('duration'), 1000)
thumbnail = xpath_text(metadata, 'episode_image_url')
if not episode: if not episode:
episode = media_metadata.get('title') episode = media_metadata.get('title')
if not episode_number: if not episode_number:
episode_number = int_or_none(media_metadata.get('episode_number')) episode_number = int_or_none(media_metadata.get('episode_number'))
if not thumbnail: thumbnail_url = try_get(media, lambda x: x['thumbnail']['url'])
thumbnail = media_metadata.get('thumbnail', {}).get('url') if thumbnail_url:
thumbnails.append({
'url': thumbnail_url,
'width': 640,
'height': 360
})
season_number = int_or_none(self._search_regex( season_number = int_or_none(self._search_regex(
r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
@ -619,7 +636,7 @@ def _real_extract(self, url):
'title': video_title, 'title': video_title,
'description': video_description, 'description': video_description,
'duration': duration, 'duration': duration,
'thumbnail': thumbnail, 'thumbnails': thumbnails,
'uploader': video_uploader, 'uploader': video_uploader,
'series': series, 'series': series,
'season': season, 'season': season,