]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/daum.py
debian/NEWS: Update with notes about split audio/video downloads.
[youtubedl] / youtube_dl / extractor / daum.py
1 # encoding: utf-8
2 import re
3 import xml.etree.ElementTree
4
5 from .common import InfoExtractor
6 from ..utils import (
7 compat_urllib_parse,
8 determine_ext,
9 )
10
11
12 class DaumIE(InfoExtractor):
13 _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
14 IE_NAME = u'daum.net'
15
16 _TEST = {
17 u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
18 u'file': u'52554690.mp4',
19 u'info_dict': {
20 u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
21 u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
22 u'upload_date': u'20130831',
23 u'duration': 3868,
24 },
25 }
26
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
29 video_id = mobj.group(1)
30 canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
31 webpage = self._download_webpage(canonical_url, video_id)
32 full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
33 webpage, u'full id')
34 query = compat_urllib_parse.urlencode({'vid': full_id})
35 info_xml = self._download_webpage(
36 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
37 u'Downloading video info')
38 urls_xml = self._download_webpage(
39 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
40 video_id, u'Downloading video formats info')
41 info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
42 urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
43
44 self.to_screen(u'%s: Getting video urls' % video_id)
45 formats = []
46 for format_el in urls.findall('result/output_list/output_list'):
47 profile = format_el.attrib['profile']
48 format_query = compat_urllib_parse.urlencode({
49 'vid': full_id,
50 'profile': profile,
51 })
52 url_xml = self._download_webpage(
53 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
54 video_id, note=False)
55 url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
56 format_url = url_doc.find('result/url').text
57 formats.append({
58 'url': format_url,
59 'ext': determine_ext(format_url),
60 'format_id': profile,
61 })
62
63 info = {
64 'id': video_id,
65 'title': info.find('TITLE').text,
66 'formats': formats,
67 'thumbnail': self._og_search_thumbnail(webpage),
68 'description': info.find('CONTENTS').text,
69 'duration': int(info.find('DURATION').text),
70 'upload_date': info.find('REGDTTM').text[:8],
71 }
72 # TODO: Remove when #980 has been merged
73 info.update(formats[-1])
74 return info