Fixed download from Dailymotion.

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 79185b1e7c8972a74261097793bc8ab44edf6239..377ceff588241ccdb37bb19f972648cc898d5873 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -858,7 +858,7 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
-       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -1056,7 +1056,7 @@ class YoutubeIE(InfoExtractor):
 
                # upload date
                upload_date = u'NA'
-               mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
+               mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
                if mobj is not None:
                        upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
                        format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
@@ -1079,7 +1079,7 @@ class YoutubeIE(InfoExtractor):
                # Decide which formats to download
                req_format = self._downloader.params.get('format', None)
 
-               if 'fmt_url_map' in video_info:
+               if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1 and ',' in video_info['fmt_url_map'][0]:
                        url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
                        format_limit = self._downloader.params.get('format_limit', None)
                        if format_limit is not None and format_limit in self._available_formats:
@@ -1320,6 +1320,7 @@ class DailymotionIE(InfoExtractor):
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)
+               request.add_header('Cookie', 'family_filter=off')
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
@@ -1329,25 +1330,29 @@ class DailymotionIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
-               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
-               mediaURL = urllib.unquote(mobj.group(1))
+               sequence = urllib.unquote(mobj.group(1))
+               mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 
-               # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
-               mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+               mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
-               mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
+               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
@@ -2620,8 +2625,8 @@ class FFmpegExtractAudioPP(PostProcessor):
        @staticmethod
        def get_audio_codec(path):
                try:
-                       handle = subprocess.Popen(['ffprobe', '-show_streams', '--', path],
-                                       stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
+                       cmd = ['ffprobe', '-show_streams', '--', path]
+                       handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
                        output = handle.communicate()[0]
                        if handle.wait() != 0:
                                return None
@@ -2638,8 +2643,8 @@ class FFmpegExtractAudioPP(PostProcessor):
        @staticmethod
        def run_ffmpeg(path, out_path, codec, more_opts):
                try:
-                       ret = subprocess.call(['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path],
-                                       stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
+                       cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
+                       ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
                        return (ret == 0)
                except (IOError, OSError):
                        return False
@@ -2723,7 +2728,7 @@ if __name__ == '__main__':
                # Parse command line
                parser = optparse.OptionParser(
                        usage='Usage: %prog [options] url...',
-                       version='2011.02.25b',
+                       version='2011.03.29',
                        conflict_handler='resolve',
                )