]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ndtv.py
95e7d63aade1edbc6a0c300bcc18168d707f8716
[youtubedl] / youtube_dl / extractor / ndtv.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 month_by_name,
8 int_or_none,
9 )
10
11
12 class NDTVIE(InfoExtractor):
13 _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
14
15 _TEST = {
16 'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710',
17 'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
18 'info_dict': {
19 'id': '300710',
20 'ext': 'mp4',
21 'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
22 'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
23 'upload_date': '20131208',
24 'duration': 1327,
25 'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg',
26 },
27 }
28
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
32
33 webpage = self._download_webpage(url, video_id)
34
35 filename = self._search_regex(
36 r"__filename='([^']+)'", webpage, 'video filename')
37 video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
38 filename)
39
40 duration = int_or_none(self._search_regex(
41 r"__duration='([^']+)'", webpage, 'duration', fatal=False))
42
43 date_m = re.search(r'''(?x)
44 <p\s+class="vod_dateline">\s*
45 Published\s+On:\s*
46 (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
47 ''', webpage)
48 upload_date = None
49
50 if date_m is not None:
51 month = month_by_name(date_m.group('monthname'))
52 if month is not None:
53 upload_date = '%s%02d%02d' % (
54 date_m.group('year'), month, int(date_m.group('day')))
55
56 description = self._og_search_description(webpage)
57 READ_MORE = ' (Read more)'
58 if description.endswith(READ_MORE):
59 description = description[:-len(READ_MORE)]
60
61 title = self._og_search_title(webpage)
62 TITLE_SUFFIX = ' - NDTV'
63 if title.endswith(TITLE_SUFFIX):
64 title = title[:-len(TITLE_SUFFIX)]
65
66 return {
67 'id': video_id,
68 'url': video_url,
69 'title': title,
70 'description': description,
71 'thumbnail': self._og_search_thumbnail(webpage),
72 'duration': duration,
73 'upload_date': upload_date,
74 }