]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/daum.py
Update changelog.
[youtubedl] / youtube_dl / extractor / daum.py
1 # encoding: utf-8
2 import re
3
4 from .common import InfoExtractor
5 from ..utils import (
6 compat_urllib_parse,
7 determine_ext,
8 )
9
10
11 class DaumIE(InfoExtractor):
12 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
13 IE_NAME = u'daum.net'
14
15 _TEST = {
16 u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
17 u'file': u'52554690.mp4',
18 u'info_dict': {
19 u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
20 u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
21 u'upload_date': u'20130831',
22 u'duration': 3868,
23 },
24 }
25
26 def _real_extract(self, url):
27 mobj = re.match(self._VALID_URL, url)
28 video_id = mobj.group(1)
29 canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
30 webpage = self._download_webpage(canonical_url, video_id)
31 full_id = self._search_regex(
32 r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
33 webpage, u'full id')
34 query = compat_urllib_parse.urlencode({'vid': full_id})
35 info = self._download_xml(
36 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
37 u'Downloading video info')
38 urls = self._download_xml(
39 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
40 video_id, u'Downloading video formats info')
41
42 self.to_screen(u'%s: Getting video urls' % video_id)
43 formats = []
44 for format_el in urls.findall('result/output_list/output_list'):
45 profile = format_el.attrib['profile']
46 format_query = compat_urllib_parse.urlencode({
47 'vid': full_id,
48 'profile': profile,
49 })
50 url_doc = self._download_xml(
51 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
52 video_id, note=False)
53 format_url = url_doc.find('result/url').text
54 formats.append({
55 'url': format_url,
56 'ext': determine_ext(format_url),
57 'format_id': profile,
58 })
59
60 return {
61 'id': video_id,
62 'title': info.find('TITLE').text,
63 'formats': formats,
64 'thumbnail': self._og_search_thumbnail(webpage),
65 'description': info.find('CONTENTS').text,
66 'duration': int(info.find('DURATION').text),
67 'upload_date': info.find('REGDTTM').text[:8],
68 }