X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=d5876ad3463b71a841b00552f0b97737b4264996;hb=7b670a4483d589af822e7fc061d1d3d3aafd36f0;hp=7c9f09f77b6d093e62e91735cf8ee8bb01db7408;hpb=41a6eb949a625983c55cdae0c06410392f3a3110;p=youtube-dl.git

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 7c9f09f77..d5876ad34 100755
--- 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)
@@ -570,7 +570,11 @@ class YoutubeIE(InfoExtractor):
         if video_description:
             video_description = clean_html(video_description)
         else:
-            video_description = ''
+            fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
+            if fd_mobj:
+                video_description = unescapeHTML(fd_mobj.group(1))
+            else:
+                video_description = u''
 
         # subtitles
         video_subtitles = None
@@ -622,8 +626,7 @@ 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 +646,9 @@ 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 +691,6 @@ 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)
@@ -1231,7 +1228,7 @@ class ArteTvIE(InfoExtractor):
 
         for (i, key, err) in matchTuples:
             if mobj.group(i) is None:
-                self._downloader.trouble(err)
+                self._downloader.report_error(err)
                 return
             else:
                 info[key] = mobj.group(i)
@@ -1245,7 +1242,7 @@ class ArteTvIE(InfoExtractor):
             r'src="(.*?/videothek_js.*?\.js)',
             0,
             [
-                (1, 'url', u'ERROR: Invalid URL: %s' % url)
+                (1, 'url', u'Invalid URL: %s' % url)
             ]
         )
         http_host = url.split('/')[2]
@@ -1257,9 +1254,9 @@ class ArteTvIE(InfoExtractor):
                 '(rtmp://.*?)\'',
             re.DOTALL,
             [
-                (1, 'path',   u'ERROR: could not extract video path: %s' % url),
-                (2, 'player', u'ERROR: could not extract video player: %s' % url),
-                (3, 'url',    u'ERROR: could not extract video url: %s' % url)
+                (1, 'path',   u'could not extract video path: %s' % url),
+                (2, 'player', u'could not extract video player: %s' % url),
+                (3, 'url',    u'could not extract video url: %s' % url)
             ]
         )
         video_url = u'%s/%s' % (info.get('url'), info.get('path'))
@@ -1271,7 +1268,7 @@ class ArteTvIE(InfoExtractor):
             r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
             0,
             [
-                (1, 'url', u'ERROR: Invalid URL: %s' % url)
+                (1, 'url', u'Invalid URL: %s' % url)
             ]
         )
         next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1280,7 +1277,7 @@ class ArteTvIE(InfoExtractor):
             r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
             0,
             [
-                (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+                (1, 'url', u'Could not find <video> tag: %s' % url)
             ]
         )
         next_url = compat_urllib_parse.unquote(info.get('url'))
@@ -1293,10 +1290,10 @@ class ArteTvIE(InfoExtractor):
                 '<url quality="hd">(.*?)</url>',
             re.DOTALL,
             [
-                (1, 'id',    u'ERROR: could not extract video id: %s' % url),
-                (2, 'title', u'ERROR: could not extract video title: %s' % url),
-                (3, 'date',  u'ERROR: could not extract video date: %s' % url),
-                (4, 'url',   u'ERROR: could not extract video url: %s' % url)
+                (1, 'id',    u'could not extract video id: %s' % url),
+                (2, 'title', u'could not extract video title: %s' % url),
+                (3, 'date',  u'could not extract video date: %s' % url),
+                (4, 'url',   u'could not extract video url: %s' % url)
             ]
         )
 
@@ -1525,7 +1522,7 @@ class YoutubeSearchIE(InfoExtractor):
             api_response = json.loads(data)['data']
 
             if not 'items' in api_response:
-                self._downloader.trouble(u'[youtube] No video results')
+                self._downloader.report_error(u'[youtube] No video results')
                 return
 
             new_ids = list(video['id'] for video in api_response['items'])
@@ -2794,7 +2791,7 @@ class SoundcloudSetIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
-            self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+            self._downloader.report_error(u'invalid URL: %s' % url)
             return
 
         # extract uploader (which is in the url)
@@ -2812,14 +2809,14 @@ class SoundcloudSetIE(InfoExtractor):
             info_json_bytes = compat_urllib_request.urlopen(request).read()
             info_json = info_json_bytes.decode('utf-8')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+            self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
             return
 
         videos = []
         info = json.loads(info_json)
         if 'errors' in info:
             for err in info['errors']:
-                self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err['error_message']))
+                self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
             return
 
         for track in info['tracks']:
@@ -2832,7 +2829,7 @@ class SoundcloudSetIE(InfoExtractor):
                 stream_json_bytes = compat_urllib_request.urlopen(request).read()
                 stream_json = stream_json_bytes.decode('utf-8')
             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
+                self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err))
                 return
 
             streams = json.loads(stream_json)
@@ -3180,7 +3177,7 @@ class MTVIE(InfoExtractor):
             format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
             video_url = rendition.find('./src').text
         except KeyError:
-            self._downloader.trouble('Invalid rendition field.')
+            self._downloader.report_error('Invalid rendition field.')
             return
 
         info = {
@@ -3627,7 +3624,7 @@ class FunnyOrDieIE(InfoExtractor):
         if not m:
             m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
             if not m:
-                self._downloader.trouble(u'Cannot find video title')
+                self._downloader.report_error(u'Cannot find video title')
         title = clean_html(m.group('title'))
 
         m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
@@ -3659,10 +3656,13 @@ 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 +3684,7 @@ 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+)'
@@ -3730,7 +3730,7 @@ class WorldStarHipHopIE(InfoExtractor):
             else:
                 ext = 'flv'
         else:
-            self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+            self._downloader.report_error(u'Cannot find video url for %s' % video_id)
             return
 
         _title = r"""<title>(.*)</title>"""
@@ -4250,7 +4250,7 @@ class LiveLeakIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
-            self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+            self._downloader.report_error(u'invalid URL: %s' % url)
             return
 
         video_id = mobj.group('video_id')
@@ -4265,7 +4265,7 @@ class LiveLeakIE(InfoExtractor):
 
         m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
         if not m:
-            self._downloader.trouble(u'Cannot find video title')
+            self._downloader.report_error(u'Cannot find video title')
         title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
 
         m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
@@ -4331,6 +4331,40 @@ 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 +4419,7 @@ def gen_extractors():
         SpiegelIE(),
         LiveLeakIE(),
         ARDIE(),
+        TumblrIE(),
         GenericIE()
     ]