diff options
| -rw-r--r-- | youtube_dl/extractor/stitcher.py | 78 |
1 files changed, 61 insertions, 17 deletions
diff --git a/youtube_dl/extractor/stitcher.py b/youtube_dl/extractor/stitcher.py index a547debbd..971a1c466 100644 --- a/youtube_dl/extractor/stitcher.py +++ b/youtube_dl/extractor/stitcher.py @@ -1,37 +1,81 @@ -# coding: utf-8 from __future__ import unicode_literals + +import re + from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + determine_ext, + int_or_none, + js_to_json, + unescapeHTML, +) class StitcherIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/[\/a-z\-]+(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)' + _TESTS = [{ 'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true', 'md5': '391dd4e021e6edeb7b8e68fbf2e9e940', 'info_dict': { 'id': '40789481', 'ext': 'mp3', - 'title': 'Machine Learning Mastery and Cancer Clusters from Talking Machines', - } - } + 'title': 'Machine Learning Mastery and Cancer Clusters', + 'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3', + 'duration': 1604, + 'thumbnail': 're:^https?://.*\.jpg', + }, + }, { + 'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true', + 'info_dict': { + 'id': '40846275', + 'display_id': 'the-rare-hourlong-comedy-plus', + 'ext': 'mp3', + 'title': "The CW's 'Crazy Ex-Girlfriend'", + 'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17', + 'duration': 2235, + 'thumbnail': 're:^https?://.*\.jpg', + }, + 'params': { + 'skip_download': True, + }, + }, { + # escaped title + 'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true', + 'only_matching': 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, + }] def _real_extract(self, url): - audio_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + audio_id = mobj.group('id') + display_id = mobj.group('display_id') or audio_id - webpage = self._download_webpage(url, audio_id) + webpage = self._download_webpage(url, display_id) - title = self._og_search_title(webpage) - url = self._search_regex(r'episodeURL: "(.+?)"', webpage, 'url') - episode_image = self._search_regex(r'episodeImage: "(.+?)"', webpage, 'episode_image', fatal=False) - duration = int_or_none(self._search_regex(r'duration: (\d+?),', webpage, 'duration', fatal=False)) + episode = self._parse_json( + js_to_json(self._search_regex( + r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')), + display_id)['config']['episode'] + + title = unescapeHTML(episode['title']) + formats = [{ + 'url': episode[episode_key], + 'ext': determine_ext(episode[episode_key]) or 'mp3', + 'vcodec': 'none', + } for episode_key in ('origEpisodeURL', '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 { 'id': audio_id, - 'url': url, + 'display_id': display_id, 'title': title, + 'description': description, 'duration': duration, - 'thumbnail': episode_image, - 'ext': 'mp3', - 'vcodec': 'none', + 'thumbnail': thumbnail, + 'formats': formats, } |