aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:02:56 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:02:56 +0200
commit462dc88b17c431b067fc197d06bd05013ced7000 (patch)
tree8e44ed45743b6b0ce1b839c9685420847711e47a /youtube_dl/extractor
parent570fa151fcd1f56cba8aaeff9f77d1e50e508e1b (diff)
Move Steam IE into its own file
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/steam.py63
1 files changed, 63 insertions, 0 deletions
diff --git a/youtube_dl/extractor/steam.py b/youtube_dl/extractor/steam.py
new file mode 100644
index 000000000..30cb83208
--- /dev/null
+++ b/youtube_dl/extractor/steam.py
@@ -0,0 +1,63 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ unescapeHTML,
+)
+
+
+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
+ """
+ _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'
+
+ @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
+
+ 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)
+
+ if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
+ videourl = self._AGECHECK_TEMPLATE % gameID
+ self.report_age_confirmation()
+ webpage = self._download_webpage(videourl, gameID)
+
+ self.report_extraction(gameID)
+ game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
+ webpage, 'game title')
+
+ 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)]