]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/daum.py
6033cd94a1b251d66e7a3f80034bc58b79fa4b55
[youtubedl] / youtube_dl / extractor / daum.py
1 # encoding: utf-8
2
3 from __future__ import unicode_literals
4
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9 compat_urllib_parse,
10 )
11
12
13 class DaumIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
15 IE_NAME = 'daum.net'
16
17 _TEST = {
18 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
19 'info_dict': {
20 'id': '52554690',
21 'ext': 'mp4',
22 'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
23 'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
24 'upload_date': '20130831',
25 'duration': 3868,
26 },
27 }
28
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group(1)
32 canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
33 webpage = self._download_webpage(canonical_url, video_id)
34 full_id = self._search_regex(
35 r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
36 webpage, 'full id')
37 query = compat_urllib_parse.urlencode({'vid': full_id})
38 info = self._download_xml(
39 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
40 'Downloading video info')
41 urls = self._download_xml(
42 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
43 video_id, 'Downloading video formats info')
44
45 self.to_screen(u'%s: Getting video urls' % video_id)
46 formats = []
47 for format_el in urls.findall('result/output_list/output_list'):
48 profile = format_el.attrib['profile']
49 format_query = compat_urllib_parse.urlencode({
50 'vid': full_id,
51 'profile': profile,
52 })
53 url_doc = self._download_xml(
54 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
55 video_id, note=False)
56 format_url = url_doc.find('result/url').text
57 formats.append({
58 'url': format_url,
59 'format_id': profile,
60 })
61
62 return {
63 'id': video_id,
64 'title': info.find('TITLE').text,
65 'formats': formats,
66 'thumbnail': self._og_search_thumbnail(webpage),
67 'description': info.find('CONTENTS').text,
68 'duration': int(info.find('DURATION').text),
69 'upload_date': info.find('REGDTTM').text[:8],
70 }