Merge pull request #386 from FiloSottile/blip

Blip.tv

diff --git a/youtube-dl b/youtube-dl
index f65e97fd077d46b2c6535f32a65b32dd50639a74..f2268af227b0eee8548aa6d106861cc508879931 100755 (executable)
Binary files a/youtube-dl and b/youtube-dl differ

diff --git a/youtube-dl.exe b/youtube-dl.exe
index 6d19ef5eacdf67d3618ce9e7b623481712abbe2e..2aa052ccf569ae513f627910c18e55675effe844 100755 (executable)
Binary files a/youtube-dl.exe and b/youtube-dl.exe differ

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 10d40fa6548f97611e6eaf9259d82fa7951196d3..ddb4aa16b9af9c8f6a24b5ed922639392f48ca54 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -182,7 +182,7 @@ class YoutubeIE(InfoExtractor):
                        end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
                        caption = unescapeHTML(caption)
                        caption = unescapeHTML(caption) # double cycle, intentional
-                       srt += str(n) + '\n'
+                       srt += str(n+1) + '\n'
                        srt += start + ' --> ' + end + '\n'
                        srt += caption + '\n\n'
                return srt
@@ -311,6 +311,11 @@ class YoutubeIE(InfoExtractor):
                                self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
                        return
 
+               # Check for "rental" videos
+               if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
+                       self._downloader.trouble(u'ERROR: "rental" videos not supported')
+                       return
+
                # Start extracting information
                self.report_information_extraction(video_id)
 
@@ -361,7 +366,8 @@ class YoutubeIE(InfoExtractor):
                                        srt_list = urllib2.urlopen(request).read()
                                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
-                               srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
+                               srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
+                               srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
                                if not srt_lang_list:
                                        raise Trouble(u'WARNING: video has no closed captions')
                                if self._downloader.params.get('subtitleslang', False):
@@ -369,14 +375,16 @@ class YoutubeIE(InfoExtractor):
                                elif 'en' in srt_lang_list:
                                        srt_lang = 'en'
                                else:
-                                       srt_lang = srt_lang_list[0]
+                                       srt_lang = srt_lang_list.keys()[0]
                                if not srt_lang in srt_lang_list:
                                        raise Trouble(u'WARNING: no closed captions found in the specified language')
-                               request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
+                               request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
                                try:
                                        srt_xml = urllib2.urlopen(request).read()
                                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                        raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+                               if not srt_xml:
+                                       raise Trouble(u'WARNING: unable to download video subtitles')
                                video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
                        except Trouble as trouble:
                                self._downloader.trouble(trouble[0])
@@ -1227,7 +1235,7 @@ class YoutubeSearchIE(InfoExtractor):
                InfoExtractor.__init__(self, downloader)
 
        def report_download_page(self, query, pagenum):
-               """Report attempt to download playlist page with given number."""
+               """Report attempt to download search page with given number."""
                query = query.decode(preferredencoding())
                self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
 
@@ -1463,8 +1471,8 @@ class YoutubePlaylistIE(InfoExtractor):
 
        _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
-       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
-       _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+       _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;list=(PL)?%s&'
+       _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
        IE_NAME = u'youtube:playlist'
 
        def __init__(self, downloader=None):
@@ -2281,12 +2289,14 @@ class EscapistIE(InfoExtractor):
 
                self.report_extraction(showName)
                try:
-                       webPageBytes = urllib2.urlopen(url).read()
+                       webPage = urllib2.urlopen(url)
+                       webPageBytes = webPage.read()
+                       m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
+                       webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
                        return
 
-               webPage = webPageBytes.decode('utf-8')
                descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
                description = unescapeHTML(descMatch.group(1))
                imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
@@ -2445,11 +2455,11 @@ class XVideosIE(InfoExtractor):
 
 
                # Extract video thumbnail
-               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
                        return
-               video_thumbnail = mobj.group(1).decode('utf-8')
+               video_thumbnail = mobj.group(0).decode('utf-8')
 
                info = {
                        'id': video_id,

diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py
index b4262f9e4f18f84466f51c8fe8108a60fa6b34b4..527dc3a3d73d4c671c922dca261046390117bdce 100644 (file)
--- a/youtube_dl/PostProcessor.py
+++ b/youtube_dl/PostProcessor.py
@@ -162,7 +162,7 @@ class FFmpegExtractAudioPP(PostProcessor):
 
                prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
                new_path = prefix + sep + extension
-               self._downloader.to_screen(u'[' + self._exes['avconv'] and 'avconv' or 'ffmpeg' + '] Destination: ' + new_path)
+               self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
                try:
                        self.run_ffmpeg(path, new_path, acodec, more_opts)
                except:
@@ -170,7 +170,7 @@ class FFmpegExtractAudioPP(PostProcessor):
                        if isinstance(e, AudioConversionError):
                                self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
                        else:
-                               self._downloader.to_stderr(u'ERROR: error running ' + self._exes['avconv'] and 'avconv' or 'ffmpeg')
+                               self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg'))
                        return None
 
                # Try to update the date time for extracted audio file.