summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/rottentomatoes.py
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-15 16:49:24 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-15 16:49:24 +0000
commit2415e66f889f38503b73e8ebc5f43ca342390e5c (patch)
treeac48ab69d1d96bae3d83756134921e0d90593aa5 /yt_dlp/extractor/rottentomatoes.py
parentInitial commit. (diff)
downloadyt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.tar.xz
yt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.zip
Adding upstream version 2024.03.10.upstream/2024.03.10
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/rottentomatoes.py')
-rw-r--r--yt_dlp/extractor/rottentomatoes.py80
1 files changed, 80 insertions, 0 deletions
diff --git a/yt_dlp/extractor/rottentomatoes.py b/yt_dlp/extractor/rottentomatoes.py
new file mode 100644
index 0000000..e357175
--- /dev/null
+++ b/yt_dlp/extractor/rottentomatoes.py
@@ -0,0 +1,80 @@
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ clean_html,
+ float_or_none,
+ get_element_by_class,
+ join_nonempty,
+ traverse_obj,
+ url_or_none,
+)
+
+
+class RottenTomatoesIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?rottentomatoes\.com/m/(?P<playlist>[^/]+)(?:/(?P<tr>trailers)(?:/(?P<id>\w+))?)?'
+
+ _TESTS = [{
+ 'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
+ 'info_dict': {
+ 'id': '11028566',
+ 'ext': 'mp4',
+ 'title': 'Toy Story 3',
+ 'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.'
+ },
+ 'skip': 'No longer available',
+ }, {
+ 'url': 'https://www.rottentomatoes.com/m/toy_story_3/trailers/VycaVoBKhGuk',
+ 'info_dict': {
+ 'id': 'VycaVoBKhGuk',
+ 'ext': 'mp4',
+ 'title': 'Toy Story 3: Trailer 2',
+ 'description': '',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'duration': 149.941
+ },
+ }, {
+ 'url': 'http://www.rottentomatoes.com/m/toy_story_3',
+ 'info_dict': {
+ 'id': 'toy_story_3',
+ 'title': 'Toy Story 3',
+ },
+ 'playlist_mincount': 4,
+ }, {
+ 'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers',
+ 'info_dict': {
+ 'id': 'toy_story_3-trailers',
+ },
+ 'playlist_mincount': 5,
+ }]
+
+ def _extract_videos(self, data, display_id):
+ for video in traverse_obj(data, (lambda _, v: v['publicId'] and v['file'] and v['type'] == 'hls')):
+ yield {
+ 'formats': self._extract_m3u8_formats(
+ video['file'], display_id, 'mp4', m3u8_id='hls', fatal=False),
+ **traverse_obj(video, {
+ 'id': 'publicId',
+ 'title': 'title',
+ 'description': 'description',
+ 'duration': ('durationInSeconds', {float_or_none}),
+ 'thumbnail': ('image', {url_or_none}),
+ }),
+ }
+
+ def _real_extract(self, url):
+ playlist_id, trailers, video_id = self._match_valid_url(url).group('playlist', 'tr', 'id')
+ playlist_id = join_nonempty(playlist_id, trailers)
+ webpage = self._download_webpage(url, playlist_id)
+ data = self._search_json(
+ r'<script[^>]+\bid=["\'](?:heroV|v)ideos["\'][^>]*>', webpage,
+ 'data', playlist_id, contains_pattern=r'\[{(?s:.+)}\]')
+
+ if video_id:
+ video_data = traverse_obj(data, lambda _, v: v['publicId'] == video_id)
+ if not video_data:
+ raise ExtractorError('Unable to extract video from webpage')
+ return next(self._extract_videos(video_data, video_id))
+
+ return self.playlist_result(
+ self._extract_videos(data, playlist_id), playlist_id,
+ clean_html(get_element_by_class('scoreboard__title', webpage)))