Move code into a separate Python module
[youtube-dl.git] / youtube-dl
index ff01775..a5af555 100755 (executable)
@@ -12,6 +12,8 @@ __author__  = (
        'Rogério Brito',
        'Philipp Hagemeister',
        'Sören Schulze',
+       'Kevin Ngo',
+       'Ori Avtalion',
        )
 
 __license__ = 'Public Domain'
@@ -1560,9 +1562,6 @@ class DailymotionIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)
@@ -1651,9 +1650,6 @@ class GoogleIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)
@@ -1758,9 +1754,6 @@ class PhotobucketIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)
@@ -1840,9 +1833,6 @@ class YahooIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url, new_video=True):
                # Extract ID from URL
                mobj = re.match(self._VALID_URL, url)
@@ -1993,9 +1983,6 @@ class VimeoIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url, new_video=True):
                # Extract ID from URL
                mobj = re.match(self._VALID_URL, url)
@@ -2118,9 +2105,6 @@ class GenericIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                # At this point we have a new video
                self._downloader.increment_downloads()
@@ -2647,9 +2631,6 @@ class DepositFilesIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                # At this point we have a new file
                self._downloader.increment_downloads()
@@ -3040,9 +3021,6 @@ class MyVideoIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self,url):
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:
@@ -3505,9 +3483,6 @@ class SoundcloudIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
 
-       def _real_initialize(self):
-               return
-
        def _real_extract(self, url):
                htmlParser = HTMLParser.HTMLParser()
 
@@ -3534,7 +3509,7 @@ class SoundcloudIE(InfoExtractor):
                self.report_extraction('%s/%s' % (uploader, slug_title))
 
                # extract uid and stream token that soundcloud hands out for access
-               mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)   
+               mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
                if mobj:
                        video_id = mobj.group(1)
                        stream_token = mobj.group(2)
@@ -3583,6 +3558,91 @@ class SoundcloudIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 
+class InfoQIE(InfoExtractor):
+       """Information extractor for infoq.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+       IE_NAME = u'infoq'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               self.report_webpage(url)
+
+               request = urllib2.Request(url)
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(url)
+
+
+               # Extract video URL
+               mobj = re.search(r"jsclassref='([^']*)'", webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+               # Extract title
+               mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+               # Extract description
+               video_description = u'No description available.'
+               mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
+               if mobj is not None:
+                       video_description = mobj.group(1).decode('utf-8')
+
+               video_filename = video_url.split('/')[-1]
+               video_id, extension = video_filename.split('.')
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': self._simplify_title(video_title),
+                       'ext': extension,
+                       'format': extension, # Extension is always(?) mp4, but seems to be flv
+                       'thumbnail': None,
+                       'description': video_description,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+
+
 class PostProcessor(object):
        """Post Processor class.
 
@@ -3980,11 +4040,12 @@ def gen_extractors():
                CollegeHumorIE(),
                XVideosIE(),
                SoundcloudIE(),
+               InfoQIE(),
 
                GenericIE()
        ]
 
-def main():
+def _real_main():
        parser, opts, args = parseOpts()
 
        # Open appropriate CookieJar
@@ -4144,10 +4205,9 @@ def main():
 
        sys.exit(retcode)
 
-
-if __name__ == '__main__':
+def main():
        try:
-               main()
+               _real_main()
        except DownloadError:
                sys.exit(1)
        except SameFileError:
@@ -4155,4 +4215,7 @@ if __name__ == '__main__':
        except KeyboardInterrupt:
                sys.exit(u'\nERROR: Interrupted by user')
 
+if __name__ == '__main__':
+       main()
+
 # vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: