[stitcher] fix extraction(closes #20811)(closes #27606)

This commit is contained in:
Remita Amine 2021-01-01 18:30:56 +01:00
parent 8c17afc471
commit d0d838638c

View File

@ -4,25 +4,28 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, clean_html,
ExtractorError,
int_or_none, int_or_none,
js_to_json, str_or_none,
unescapeHTML, try_get,
) )
class StitcherIE(InfoExtractor): class StitcherIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)' _VALID_URL = r'https?://(?:www\.)?stitcher\.com/(?:podcast|show)/(?:[^/]+/)+e(?:pisode)?/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true', 'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
'md5': '391dd4e021e6edeb7b8e68fbf2e9e940', 'md5': 'e9635098e0da10b21a0e2b85585530f6',
'info_dict': { 'info_dict': {
'id': '40789481', 'id': '40789481',
'ext': 'mp3', 'ext': 'mp3',
'title': 'Machine Learning Mastery and Cancer Clusters', 'title': 'Machine Learning Mastery and Cancer Clusters',
'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3', 'description': 'md5:547adb4081864be114ae3831b4c2b42f',
'duration': 1604, 'duration': 1604,
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'upload_date': '20180126',
'timestamp': 1516989316,
}, },
}, { }, {
'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true', 'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
@ -38,6 +41,7 @@ class StitcherIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Page Not Found',
}, { }, {
# escaped title # escaped title
'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true', 'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
@ -45,37 +49,39 @@ class StitcherIE(InfoExtractor):
}, { }, {
'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true', 'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.stitcher.com/show/threedom/episode/circles-on-a-stick-200212584',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) display_id, audio_id = re.match(self._VALID_URL, url).groups()
audio_id = mobj.group('id')
display_id = mobj.group('display_id') or audio_id
webpage = self._download_webpage(url, display_id) resp = self._download_json(
'https://api.prod.stitcher.com/episode/' + audio_id,
display_id or audio_id)
episode = try_get(resp, lambda x: x['data']['episodes'][0], dict)
if not episode:
raise ExtractorError(resp['errors'][0]['message'], expected=True)
episode = self._parse_json( title = episode['title'].strip()
js_to_json(self._search_regex( audio_url = episode['audio_url']
r'(?s)var\s+stitcher(?:Config)?\s*=\s*({.+?});\n', webpage, 'episode config')),
display_id)['config']['episode']
title = unescapeHTML(episode['title']) thumbnail = None
formats = [{ show_id = episode.get('show_id')
'url': episode[episode_key], if show_id and episode.get('classic_id') != -1:
'ext': determine_ext(episode[episode_key]) or 'mp3', thumbnail = 'https://stitcher-classic.imgix.net/feedimages/%s.jpg' % show_id
'vcodec': 'none',
} for episode_key in ('episodeURL',) if episode.get(episode_key)]
description = self._search_regex(
r'Episode Info:\s*</span>([^<]+)<', webpage, 'description', fatal=False)
duration = int_or_none(episode.get('duration'))
thumbnail = episode.get('episodeImage')
return { return {
'id': audio_id, 'id': audio_id,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'description': description, 'description': clean_html(episode.get('html_description') or episode.get('description')),
'duration': duration, 'duration': int_or_none(episode.get('duration')),
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'formats': formats, 'url': audio_url,
'vcodec': 'none',
'timestamp': int_or_none(episode.get('date_created')),
'season_number': int_or_none(episode.get('season')),
'season_id': str_or_none(episode.get('season_id')),
} }