jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[steam] Add support for steamcommunity.com (Fixes #2757)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-21 02:34:34 +02:00
parent 0610a3e0b2
commit 1f27d2c0e1
1 changed files with 78 additions and 41 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

119
youtube_dl/extractor/steam.py
View file

@ -10,15 +10,18 @@ from ..utils import (
class SteamIE(InfoExtractor): class SteamIE(InfoExtractor):
_VALID_URL = r"""(?x)http://store\.steampowered\.com/ _VALID_URL = r"""(?x)
(agecheck/)? https?://store\.steampowered\.com/
(?P<urltype>video|app)/ #If the page is only for videos or for a game (agecheck/)?
(?P<gameID>\d+)/? (?P<urltype>video|app)/ #If the page is only for videos or for a game
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID (?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/' _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' _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
_TEST = { _TESTS = [{
"url": "http://store.steampowered.com/video/105600/", "url": "http://store.steampowered.com/video/105600/",
"playlist": [ "playlist": [
{ {
@ -43,44 +46,78 @@ class SteamIE(InfoExtractor):
'params': { 'params': {
'playlistend': 2, '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): def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE) m = re.match(self._VALID_URL, url)
gameID = m.group('gameID') fileID = m.group('fileID')
if fileID:
videourl = self._VIDEO_PAGE_TEMPLATE % gameID videourl = url
webpage = self._download_webpage(videourl, gameID) 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: 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() self.report_age_confirmation()
webpage = self._download_webpage(videourl, gameID) webpage = self._download_webpage(videourl, playlist_id)
self.report_extraction(gameID) if fileID:
game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>', playlist_title = self._html_search_regex(
webpage, 'game title') 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( mweb = re.finditer(r'''(?x)
r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},", 'movie_(?P<videoID>[0-9]+)':\s*\{\s*
webpage) FILENAME:\s*"(?P<videoURL>[\w:/\.\?=]+)"
titles = re.finditer( (,\s*MOVIE_NAME:\s*\"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},
r'<span class="title">(?P<videoName>.+?)</span>', webpage) ''', webpage)
thumbs = re.finditer( titles = re.finditer(
r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">', webpage) r'<span class="title">(?P<videoName>.+?)</span>', webpage)
videos = [] thumbs = re.finditer(
for vid, vtitle, thumb in zip(mweb, titles, thumbs): r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">', webpage)
video_id = vid.group('videoID') videos = []
title = vtitle.group('videoName')
video_url = vid.group('videoURL') for vid, vtitle, thumb in zip(mweb, titles, thumbs):
video_thumb = thumb.group('thumbnail') video_id = vid.group('videoID')
if not video_url: title = vtitle.group('videoName')
raise ExtractorError('Cannot find video url for %s' % video_id) video_url = vid.group('videoURL')
videos.append({ video_thumb = thumb.group('thumbnail')
'id': video_id, if not video_url:
'url': video_url, raise ExtractorError('Cannot find video url for %s' % video_id)
'ext': 'flv', videos.append({
'title': unescapeHTML(title), 'id': video_id,
'thumbnail': video_thumb 'url': video_url,
}) 'ext': 'flv',
return self.playlist_result(videos, gameID, game_title) 'title': unescapeHTML(title),
'thumbnail': video_thumb
})
if not videos:
raise ExtractorError('Could not find any videos')
return self.playlist_result(videos, playlist_id, playlist_title)