.+?)(?P=q_quality))?
- ''', playerpage):
- url = media.group('url')
- type_ = media.group('type')
- ext = media.group('ext')
- res = media.group('quality')
- f = {
- 'format_id': '%s_%s' % (res, ext) if res else ext,
- 'url': url,
- 'ext': ext,
- 'vcodec': 'none' if type_ == 'audio' else None,
- }
- f.update(self._FORMATS.get(res, {}))
- formats.append(f)
- thumbnail = self._og_search_thumbnail(playerpage)
- title = self._og_search_title(webpage).strip()
- description = self._og_search_description(webpage).strip()
- else:
+ DOWNLOAD_REGEX = r'(?s)Wir bieten dieses (?PVideo|Audio) in folgenden Formaten zum Download an:
\s*(?P.*?)
\s*'
+
+ webpage_type = self._og_search_property('type', webpage, default=None)
+ if webpage_type == 'website': # Article
+ entries = []
+ for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
+ r'(?s)]+class="infotext"[^>]*>\s*(?:]+>)?\s*(.+?).*?
.*?%s' % DOWNLOAD_REGEX,
+ webpage), 1):
+ entries.append({
+ 'id': '%s-%d' % (display_id, num),
+ 'title': '%s' % entry_title,
+ 'formats': self._extract_formats(download_text, media_kind),
+ })
+ if len(entries) > 1:
+ return self.playlist_result(entries, display_id, title)
+ formats = entries[0]['formats']
+ else: # Assume single video
download_text = self._search_regex(
- r'(?s)Wir bieten dieses Video in folgenden Formaten zum Download an:
\s*(.*?)
\s*',
- webpage, 'download links')
- links = re.finditer(
- r'
',
- download_text)
- formats = []
- for l in links:
- format_id = self._search_regex(
- r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
- format = {
- 'format_id': format_id,
- 'url': l.group('url'),
- 'format_name': l.group('name'),
- }
- m = re.match(
- r'''(?x)
- Video:\s*(?P[a-zA-Z0-9/._-]+)\s*&\#10;
- (?P[0-9]+)x(?P[0-9]+)px&\#10;
- (?P[0-9]+)kbps&\#10;
- Audio:\s*(?P[0-9]+)kbps,\s*(?P[A-Za-z\.0-9]+)&\#10;
- Größe:\s*(?P[0-9.,]+\s+[a-zA-Z]*B)''',
- l.group('title'))
- if m:
- format.update({
- 'format_note': m.group('audio_desc'),
- 'vcodec': m.group('vcodec'),
- 'width': int(m.group('width')),
- 'height': int(m.group('height')),
- 'abr': int(m.group('abr')),
- 'vbr': int(m.group('vbr')),
- 'filesize_approx': parse_filesize(m.group('filesize_approx')),
- })
- formats.append(format)
- thumbnail = self._og_search_thumbnail(webpage)
- description = self._html_search_regex(
- r'(?s)(.*?)
',
- webpage, 'description', default=None)
- title = self._html_search_regex(
- r'(.*?)', webpage, 'title')
+ DOWNLOAD_REGEX, webpage, 'download links', group='links')
+ media_kind = self._search_regex(
+ DOWNLOAD_REGEX, webpage, 'media kind', default='Video', group='kind')
+ formats = self._extract_formats(download_text, media_kind)
+ thumbnail = self._og_search_thumbnail(webpage)
+ description = self._html_search_regex(
+ r'(?s)(.*?)
',
+ webpage, 'description', default=None)
self._sort_formats(formats)
diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py
index 1793a878c..fa99b0c2a 100644
--- a/youtube_dl/postprocessor/ffmpeg.py
+++ b/youtube_dl/postprocessor/ffmpeg.py
@@ -389,23 +389,30 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
class FFmpegMetadataPP(FFmpegPostProcessor):
def run(self, info):
metadata = {}
- if info.get('title') is not None:
- metadata['title'] = info['title']
- if info.get('upload_date') is not None:
- metadata['date'] = info['upload_date']
- if info.get('artist') is not None:
- metadata['artist'] = info['artist']
- elif info.get('uploader') is not None:
- metadata['artist'] = info['uploader']
- elif info.get('uploader_id') is not None:
- metadata['artist'] = info['uploader_id']
- if info.get('description') is not None:
- metadata['description'] = info['description']
- metadata['comment'] = info['description']
- if info.get('webpage_url') is not None:
- metadata['purl'] = info['webpage_url']
- if info.get('album') is not None:
- metadata['album'] = info['album']
+
+ def add(meta_list, info_list=None):
+ if not info_list:
+ info_list = meta_list
+ if not isinstance(meta_list, (list, tuple)):
+ meta_list = (meta_list,)
+ if not isinstance(info_list, (list, tuple)):
+ info_list = (info_list,)
+ for info_f in info_list:
+ if info.get(info_f) is not None:
+ for meta_f in meta_list:
+ metadata[meta_f] = info[info_f]
+ break
+
+ add('title', ('track', 'title'))
+ add('date', 'upload_date')
+ add(('description', 'comment'), 'description')
+ add('purl', 'webpage_url')
+ add('track', 'track_number')
+ add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
+ add('genre')
+ add('album')
+ add('album_artist')
+ add('disc', 'disc_number')
if not metadata:
self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')