diff options
Diffstat (limited to 'youtube_dl/extractor/steam.py')
| -rw-r--r-- | youtube_dl/extractor/steam.py | 158 |
1 files changed, 98 insertions, 60 deletions
diff --git a/youtube_dl/extractor/steam.py b/youtube_dl/extractor/steam.py index 91658f892..1d8d57224 100644 --- a/youtube_dl/extractor/steam.py +++ b/youtube_dl/extractor/steam.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -8,78 +10,114 @@ from ..utils import ( class SteamIE(InfoExtractor): - _VALID_URL = r"""http://store\.steampowered\.com/ - (agecheck/)? - (?P<urltype>video|app)/ #If the page is only for videos or for a game - (?P<gameID>\d+)/? - (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID - """ + _VALID_URL = r"""(?x) + https?://store\.steampowered\.com/ + (agecheck/)? + (?P<urltype>video|app)/ #If the page is only for videos or for a game + (?P<gameID>\d+)/? + (?P<videoID>\d*)(?P<extra>\??) # For urltype == video we sometimes get the videoID + | + https?://(?:www\.)?steamcommunity\.com/sharedfiles/filedetails/\?id=(?P<fileID>[0-9]+) + """ _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/' _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' - _TEST = { - u"url": u"http://store.steampowered.com/video/105600/", - u"playlist": [ + _TESTS = [{ + "url": "http://store.steampowered.com/video/105600/", + "playlist": [ { - u"file": u"81300.flv", - u"md5": u"f870007cee7065d7c76b88f0a45ecc07", - u"info_dict": { - u"title": u"Terraria 1.1 Trailer", - u'playlist_index': 1, + "md5": "f870007cee7065d7c76b88f0a45ecc07", + "info_dict": { + 'id': '81300', + 'ext': 'flv', + "title": "Terraria 1.1 Trailer", + 'playlist_index': 1, } }, { - u"file": u"80859.flv", - u"md5": u"61aaf31a5c5c3041afb58fb83cbb5751", - u"info_dict": { - u"title": u"Terraria Trailer", - u'playlist_index': 2, + "md5": "61aaf31a5c5c3041afb58fb83cbb5751", + "info_dict": { + 'id': '80859', + 'ext': 'flv', + "title": "Terraria Trailer", + 'playlist_index': 2, } } - ] - } - - - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url, re.VERBOSE) is not None + ], + 'params': { + 'playlistend': 2, + } + }, { + 'url': 'http://steamcommunity.com/sharedfiles/filedetails/?id=242472205', + 'info_dict': { + 'id': 'WB5DvDOOvAY', + 'ext': 'mp4', + 'upload_date': '20140329', + 'title': 'FRONTIERS - Final Greenlight Trailer', + 'description': "The final trailer for the Steam Greenlight launch. Hooray, progress! Here's the official Greenlight page: http://steamcommunity.com/sharedfiles/filedetails/?id=242472205", + 'uploader': 'AAD Productions', + 'uploader_id': 'AtomicAgeDogGames', + } + }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url, re.VERBOSE) - gameID = m.group('gameID') - - videourl = self._VIDEO_PAGE_TEMPLATE % gameID - webpage = self._download_webpage(videourl, gameID) + m = re.match(self._VALID_URL, url) + fileID = m.group('fileID') + if fileID: + videourl = url + playlist_id = fileID + else: + gameID = m.group('gameID') + playlist_id = gameID + videourl = self._VIDEO_PAGE_TEMPLATE % playlist_id + webpage = self._download_webpage(videourl, playlist_id) if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None: - videourl = self._AGECHECK_TEMPLATE % gameID + videourl = self._AGECHECK_TEMPLATE % playlist_id self.report_age_confirmation() - webpage = self._download_webpage(videourl, gameID) + webpage = self._download_webpage(videourl, playlist_id) + + if fileID: + playlist_title = self._html_search_regex( + r'<div class="workshopItemTitle">(.+)</div>', webpage, 'title') + mweb = re.finditer(r'''(?x) + 'movie_(?P<videoID>[0-9]+)':\s*\{\s* + YOUTUBE_VIDEO_ID:\s*"(?P<youtube_id>[^"]+)", + ''', webpage) + videos = [{ + '_type': 'url', + 'url': vid.group('youtube_id'), + 'ie_key': 'Youtube', + } for vid in mweb] + else: + playlist_title = self._html_search_regex( + r'<h2 class="pageheader">(.*?)</h2>', webpage, 'game title') + + mweb = re.finditer(r'''(?x) + 'movie_(?P<videoID>[0-9]+)':\s*\{\s* + FILENAME:\s*"(?P<videoURL>[\w:/\.\?=]+)" + (,\s*MOVIE_NAME:\s*\"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}, + ''', webpage) + titles = re.finditer( + r'<span class="title">(?P<videoName>.+?)</span>', webpage) + thumbs = re.finditer( + r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">', webpage) + videos = [] - self.report_extraction(gameID) - game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>', - webpage, 'game title') + for vid, vtitle, thumb in zip(mweb, titles, thumbs): + video_id = vid.group('videoID') + title = vtitle.group('videoName') + video_url = vid.group('videoURL') + video_thumb = thumb.group('thumbnail') + if not video_url: + raise ExtractorError('Cannot find video url for %s' % video_id) + videos.append({ + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': unescapeHTML(title), + 'thumbnail': video_thumb + }) + if not videos: + raise ExtractorError('Could not find any videos') - urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," - mweb = re.finditer(urlRE, webpage) - namesRE = r'<span class="title">(?P<videoName>.+?)</span>' - titles = re.finditer(namesRE, webpage) - thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">' - thumbs = re.finditer(thumbsRE, webpage) - videos = [] - for vid,vtitle,thumb in zip(mweb,titles,thumbs): - video_id = vid.group('videoID') - title = vtitle.group('videoName') - video_url = vid.group('videoURL') - video_thumb = thumb.group('thumbnail') - if not video_url: - raise ExtractorError(u'Cannot find video url for %s' % video_id) - info = { - 'id':video_id, - 'url':video_url, - 'ext': 'flv', - 'title': unescapeHTML(title), - 'thumbnail': video_thumb - } - videos.append(info) - return [self.playlist_result(videos, gameID, game_title)] + return self.playlist_result(videos, playlist_id, playlist_title) |