etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-22 06:00:00 +00:00
Code Issues Projects Releases Wiki Activity

[ndtv] Fix extraction

Browse source
This commit is contained in:
Sergey M․ 2016-05-19 04:34:19 +06:00
parent 46bc9b7d7c
commit dd81769c62
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 11 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
youtube_dl/extractor/ndtv.py
View file

@ -1,19 +1,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
month_by_name,
int_or_none, int_or_none,
remove_end,
unified_strdate,
) )
class NDTVIE(InfoExtractor): class NDTVIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)' _VALID_URL = r'https?://(?:www\.)?ndtv\.com/video/(?:[^/]+/)+[^/?^&]+-(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710', 'url': 'http://www.ndtv.com/video/news/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal-300710',
'md5': '39f992dbe5fb531c395d8bbedb1e5e88', 'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
'info_dict': { 'info_dict': {
'id': '300710', 'id': '300710',
@ -22,7 +21,7 @@ class NDTVIE(InfoExtractor):
'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02', 'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
'upload_date': '20131208', 'upload_date': '20131208',
'duration': 1327, 'duration': 1327,
'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg', 'thumbnail': 're:https?://.*\.jpg',
}, },
} }
@ -30,36 +29,19 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' - NDTV')
filename = self._search_regex( filename = self._search_regex(
r"__filename='([^']+)'", webpage, 'video filename') r"__filename='([^']+)'", webpage, 'video filename')
video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % video_url = 'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % filename
filename)
duration = int_or_none(self._search_regex( duration = int_or_none(self._search_regex(
r"__duration='([^']+)'", webpage, 'duration', fatal=False)) r"__duration='([^']+)'", webpage, 'duration', fatal=False))
date_m = re.search(r'''(?x) upload_date = unified_strdate(self._html_search_meta(
<p\s+class="vod_dateline">\s* 'publish-date', webpage, 'upload date', fatal=False))
Published\s+On:\s*
(?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
''', webpage)
upload_date = None
if date_m is not None: description = remove_end(self._og_search_description(webpage), ' (Read more)')
month = month_by_name(date_m.group('monthname'))
if month is not None:
upload_date = '%s%02d%02d' % (
date_m.group('year'), month, int(date_m.group('day')))
description = self._og_search_description(webpage)
READ_MORE = ' (Read more)'
if description.endswith(READ_MORE):
description = description[:-len(READ_MORE)]
title = self._og_search_title(webpage)
TITLE_SUFFIX = ' - NDTV'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
return { return {
'id': video_id, 'id': video_id,