Do not try to re-encode unicode filenames (Closes #13)

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 7ac27b5..2a11604 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -11,10 +11,11 @@ __author__  = (
        'Gergely Imreh',
        'Rogério Brito',
        'Philipp Hagemeister',
+       'Sören Schulze',
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.08.28-phihag'
+__version__ = '2011.09.06-phihag'
 
 UPDATE_URL = 'https://raw.github.com/phihag/youtube-dl/master/youtube-dl'
 
@@ -456,16 +457,6 @@ class FileDownloader(object):
                self.params = params
 
        @staticmethod
-       def pmkdir(filename):
-               """Create directory components in filename. Similar to Unix "mkdir -p"."""
-               components = filename.split(os.sep)
-               aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
-               aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
-               for dir in aggregate:
-                       if not os.path.exists(dir):
-                               os.mkdir(dir)
-
-       @staticmethod
        def format_bytes(bytes):
                if bytes is None:
                        return 'N/A'
@@ -721,9 +712,11 @@ class FileDownloader(object):
                        return
 
                try:
-                       self.pmkdir(filename)
+                       dn = os.path.dirname(filename)
+                       if dn != '' and not os.path.exists(dn):
+                               os.makedirs(dn)
                except (OSError, IOError), err:
-                       self.trouble(u'ERROR: unable to create directories: %s' % str(err))
+                       self.trouble(u'ERROR: unable to create directory ' + unicode(err))
                        return
 
                if self.params.get('writedescription', False):
@@ -736,7 +729,7 @@ class FileDownloader(object):
                                finally:
                                        descfile.close()
                        except (OSError, IOError):
-                               self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn))
+                               self.trouble(u'ERROR: Cannot write description file ' + descfn)
                                return
 
                if self.params.get('writeinfojson', False):
@@ -754,7 +747,7 @@ class FileDownloader(object):
                                finally:
                                        infof.close()
                        except (OSError, IOError):
-                               self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn))
+                               self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
                                return
 
                try:
@@ -2962,6 +2955,82 @@ class BlipTVIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 
+class MyVideoIE(InfoExtractor):
+       """Information Extractor for myvideo.de."""
+
+       _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+       
+       @staticmethod
+       def suitable(url):
+               return (re.match(MyVideoIE._VALID_URL, url) is not None)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """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:
+                       self._download.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               video_id = mobj.group(1)
+               simple_title = mobj.group(2).decode('utf-8')
+               # should actually not be necessary
+               simple_title = sanitize_title(simple_title)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
+
+               # Get video webpage
+               request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+               mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+                                webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+               mobj = re.search('<title>([^<]+)</title>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+
+               video_title = mobj.group(1)
+               video_title = sanitize_title(video_title)
+
+               try:
+                       print(video_url)
+                       self._downloader.process_info({
+                               'id':           video_id,
+                               'url':          video_url,
+                               'uploader':     u'NA',
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'flv',
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'\nERROR: Unable to download video')
+
 class PostProcessor(object):
        """Post Processor class.
 
@@ -3377,6 +3446,8 @@ def main():
        facebook_ie = FacebookIE()
        bliptv_ie = BlipTVIE()
        vimeo_ie = VimeoIE()
+       myvideo_ie = MyVideoIE()
+
        generic_ie = GenericIE()
 
        # File downloader
@@ -3433,6 +3504,7 @@ def main():
        fd.add_info_extractor(facebook_ie)
        fd.add_info_extractor(bliptv_ie)
        fd.add_info_extractor(vimeo_ie)
+       fd.add_info_extractor(myvideo_ie)
 
        # This must come last since it's the
        # fallback if none of the others work