TumblrIE

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 7c9f09f77b6d093e62e91735cf8ee8bb01db7408..6a6545c9b578fba948962542d602bc5352b86840 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -152,6 +152,10 @@ class InfoExtractor(object):
         """Report information extraction."""
         self.to_screen(u'%s: Extracting information' % id_or_name)
 
+    def report_age_confirmation(self):
+        """Report attempt to confirm age."""
+        self.to_screen(u'Confirming age')
+
     #Methods for following #608
     #They set the correct value of the '_type' key
     def video_result(self, video_info):
@@ -250,10 +254,6 @@ class YoutubeIE(InfoExtractor):
         """Report attempt to log in."""
         self.to_screen(u'Logging in')
 
-    def report_age_confirmation(self):
-        """Report attempt to confirm age."""
-        self.to_screen(u'Confirming age')
-
     def report_video_webpage_download(self, video_id):
         """Report attempt to download video webpage."""
         self.to_screen(u'%s: Downloading video webpage' % video_id)
@@ -622,8 +622,7 @@ class YoutubeIE(InfoExtractor):
                 format_list = available_formats
             existing_formats = [x for x in format_list if x in url_map]
             if len(existing_formats) == 0:
-                self._downloader.report_error(u'no known formats available for video')
-                return
+                raise ExtractorError(u'no known formats available for video')
             if self._downloader.params.get('listformats', None):
                 self._print_formats(existing_formats)
                 return
@@ -643,11 +642,9 @@ class YoutubeIE(InfoExtractor):
                         video_url_list = [(rf, url_map[rf])]
                         break
                 if video_url_list is None:
-                    self._downloader.report_error(u'requested format not available')
-                    return
+                    raise ExtractorError(u'requested format not available')
         else:
-            self._downloader.report_error(u'no conn or url_encoded_fmt_stream_map information found in video info')
-            return
+            raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
 
         results = []
         for format_param, video_real_url in video_url_list:
@@ -690,10 +687,6 @@ class MetacafeIE(InfoExtractor):
         """Report disclaimer retrieval."""
         self.to_screen(u'Retrieving disclaimer')
 
-    def report_age_confirmation(self):
-        """Report attempt to confirm age."""
-        self.to_screen(u'Confirming age')
-
     def report_download_webpage(self, video_id):
         """Report webpage download."""
         self.to_screen(u'%s: Downloading webpage' % video_id)
@@ -3659,10 +3652,13 @@ class SteamIE(InfoExtractor):
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url, re.VERBOSE)
-        urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
         gameID = m.group('gameID')
-        videourl = 'http://store.steampowered.com/video/%s/' % gameID
+        videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
+        self.report_age_confirmation()
         webpage = self._download_webpage(videourl, gameID)
+        game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('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)
@@ -3684,7 +3680,7 @@ class SteamIE(InfoExtractor):
                 'thumbnail': video_thumb
                   }
             videos.append(info)
-        return videos
+        return [self.playlist_result(videos, gameID, game_title)]
 
 class UstreamIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
@@ -4331,6 +4327,40 @@ class ARDIE(InfoExtractor):
             info["url"] = stream["video_url"]
         return [info]
 
+class TumblrIE(InfoExtractor):
+    _VALID_URL = r'http://(?P<blog_name>.*?).tumblr.com/((post)|(video))/(?P<id>\d*)/(.*?)'
+
+    def _real_extract(self, url):
+        m_url = re.match(self._VALID_URL, url)
+        video_id = m_url.group('id')
+        blog = m_url.group('blog_name')
+
+        url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        re_video = r'src=\\x22(?P<video_url>http://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
+        video = re.search(re_video, webpage)
+        if video is None:
+            self.to_screen("No video founded")
+            return []
+        video_url = video.group('video_url')
+        ext = video.group('ext')
+
+        re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22'  # We pick the first poster
+        thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
+
+        # The only place where you can get a title, it's not complete,
+        # but searching in other places doesn't work for all videos
+        re_title = r'<title>(.*?) - (?P<title>.*?)</title>'
+        title = unescapeHTML(re.search(re_title, webpage).group('title'))
+
+        return [{'id': video_id,
+                 'url': video_url,
+                 'title': title,
+                 'thumbnail': thumb,
+                 'ext': ext
+                 }]
+
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
@@ -4385,6 +4415,7 @@ def gen_extractors():
         SpiegelIE(),
         LiveLeakIE(),
         ARDIE(),
+        TumblrIE(),
         GenericIE()
     ]