import re
-from .subtitles import SubtitlesInfoExtractor
+from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
return '{http://search.yahoo.com/mrss/}%s' % tag
-class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
+class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
@staticmethod
try:
_, _, ext = rendition.attrib['type'].partition('/')
rtmp_video_url = rendition.find('./src').text
- formats.append({'ext': ext,
- 'url': self._transform_rtmp_url(rtmp_video_url),
- 'format_id': rendition.get('bitrate'),
- 'width': int(rendition.get('width')),
- 'height': int(rendition.get('height')),
- })
+ if rtmp_video_url.endswith('siteunavail.png'):
+ continue
+ formats.append({
+ 'ext': ext,
+ 'url': self._transform_rtmp_url(rtmp_video_url),
+ 'format_id': rendition.get('bitrate'),
+ 'width': int(rendition.get('width')),
+ 'height': int(rendition.get('height')),
+ })
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
self._sort_formats(formats)
def _extract_subtitles(self, mdoc, mtvn_id):
subtitles = {}
- FORMATS = {
- 'scc': 'cea-608',
- 'eia-608': 'cea-608',
- 'xml': 'ttml',
- }
- subtitles_format = FORMATS.get(
- self._downloader.params.get('subtitlesformat'), 'ttml')
for transcript in mdoc.findall('.//transcript'):
if transcript.get('kind') != 'captions':
continue
lang = transcript.get('srclang')
- for typographic in transcript.findall('./typographic'):
- captions_format = typographic.get('format')
- if captions_format == subtitles_format:
- subtitles[lang] = compat_str(typographic.get('src'))
- break
- if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(mtvn_id, subtitles)
- return self.extract_subtitles(mtvn_id, subtitles)
+ subtitles[lang] = [{
+ 'url': compat_str(typographic.get('src')),
+ 'ext': typographic.get('format')
+ } for typographic in transcript.findall('./typographic')]
+ return subtitles
def _get_video_info(self, itemdoc):
uri = itemdoc.find('guid').text
webpage, 'mgid')
videos_info = self._get_videos_info(mgid)
- if self._downloader.params.get('listsubtitles', False):
- return
return videos_info
_TESTS = [
{
'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
- 'file': '853555.mp4',
'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
'info_dict': {
+ 'id': '853555',
+ 'ext': 'mp4',
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
},
},
- {
- 'add_ie': ['Vevo'],
- 'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
- 'file': 'USCJY1331283.mp4',
- 'md5': '73b4e7fcadd88929292fe52c3ced8caf',
- 'info_dict': {
- 'title': 'Everything Has Changed',
- 'upload_date': '20130606',
- 'uploader': 'Taylor Swift',
- },
- 'skip': 'VEVO is only available in some countries',
- },
]
def _get_thumbnail_url(self, uri, itemdoc):
webpage = self._download_webpage(url, video_id)
# Some videos come from Vevo.com
- m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
- webpage, re.DOTALL)
+ m_vevo = re.search(
+ r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
if m_vevo:
vevo_id = m_vevo.group(1)
self.to_screen('Vevo video detected: %s' % vevo_id)