Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[mtv] Extract subtitles (Closes #4811)

Browse Source
This commit is contained in:
Sergey M․ 2015-01-30 21:57:59 +06:00
parent 20b4492c71
commit e525d9a3df
1 changed files with 31 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
youtube_dl/extractor/mtv.py
View File

@ -2,10 +2,11 @@
import re import re
from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
compat_str,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
@ -22,7 +23,7 @@ def _media_xml_tag(tag):
return '{http://search.yahoo.com/mrss/}%s' % tag return '{http://search.yahoo.com/mrss/}%s' % tag
class MTVServicesInfoExtractor(InfoExtractor): class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
_MOBILE_TEMPLATE = None _MOBILE_TEMPLATE = None
@staticmethod @staticmethod
@ -89,6 +90,28 @@ def _extract_video_formats(self, mdoc, mtvn_id):
self._sort_formats(formats) self._sort_formats(formats)
return formats return 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)
def _get_video_info(self, itemdoc): def _get_video_info(self, itemdoc):
uri = itemdoc.find('guid').text uri = itemdoc.find('guid').text
video_id = self._id_from_uri(uri) video_id = self._id_from_uri(uri)
@ -135,6 +158,7 @@ def _get_video_info(self, itemdoc):
return { return {
'title': title, 'title': title,
'formats': self._extract_video_formats(mediagen_doc, mtvn_id), 'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
'id': video_id, 'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description, 'description': description,
@ -167,7 +191,11 @@ def _real_extract(self, url):
mgid = self._search_regex( mgid = self._search_regex(
[r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'], [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
webpage, 'mgid') webpage, 'mgid')
return self._get_videos_info(mgid)
videos_info = self._get_videos_info(mgid)
if self._downloader.params.get('listsubtitles', False):
return
return videos_info
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):