2013-09-04 22:06:50 +02:00
|
|
|
# encoding: utf-8
|
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import (
|
|
|
|
compat_urllib_parse,
|
|
|
|
determine_ext,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class DaumIE(InfoExtractor):
|
2013-12-12 13:05:38 +01:00
|
|
|
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
|
2013-09-04 22:06:50 +02:00
|
|
|
IE_NAME = u'daum.net'
|
|
|
|
|
|
|
|
_TEST = {
|
|
|
|
u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
|
|
|
|
u'file': u'52554690.mp4',
|
|
|
|
u'info_dict': {
|
|
|
|
u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
|
2013-09-05 10:08:17 +02:00
|
|
|
u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
|
2013-09-04 22:06:50 +02:00
|
|
|
u'upload_date': u'20130831',
|
|
|
|
u'duration': 3868,
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group(1)
|
2013-09-05 10:08:17 +02:00
|
|
|
canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
|
|
|
|
webpage = self._download_webpage(canonical_url, video_id)
|
2013-12-03 14:16:58 +01:00
|
|
|
full_id = self._search_regex(
|
|
|
|
r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
|
2013-09-04 22:06:50 +02:00
|
|
|
webpage, u'full id')
|
|
|
|
query = compat_urllib_parse.urlencode({'vid': full_id})
|
2013-11-26 18:48:52 +01:00
|
|
|
info = self._download_xml(
|
2013-09-04 22:06:50 +02:00
|
|
|
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
|
|
|
|
u'Downloading video info')
|
2013-11-26 18:48:52 +01:00
|
|
|
urls = self._download_xml(
|
2013-09-04 22:06:50 +02:00
|
|
|
'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
|
|
|
|
video_id, u'Downloading video formats info')
|
|
|
|
|
|
|
|
self.to_screen(u'%s: Getting video urls' % video_id)
|
|
|
|
formats = []
|
|
|
|
for format_el in urls.findall('result/output_list/output_list'):
|
|
|
|
profile = format_el.attrib['profile']
|
|
|
|
format_query = compat_urllib_parse.urlencode({
|
|
|
|
'vid': full_id,
|
|
|
|
'profile': profile,
|
|
|
|
})
|
2013-11-26 18:48:52 +01:00
|
|
|
url_doc = self._download_xml(
|
2013-09-04 22:06:50 +02:00
|
|
|
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
|
|
|
|
video_id, note=False)
|
|
|
|
format_url = url_doc.find('result/url').text
|
|
|
|
formats.append({
|
|
|
|
'url': format_url,
|
|
|
|
'ext': determine_ext(format_url),
|
|
|
|
'format_id': profile,
|
|
|
|
})
|
|
|
|
|
2013-12-03 14:21:06 +01:00
|
|
|
return {
|
2013-09-04 22:06:50 +02:00
|
|
|
'id': video_id,
|
|
|
|
'title': info.find('TITLE').text,
|
|
|
|
'formats': formats,
|
|
|
|
'thumbnail': self._og_search_thumbnail(webpage),
|
2013-09-05 10:08:17 +02:00
|
|
|
'description': info.find('CONTENTS').text,
|
2013-09-04 22:06:50 +02:00
|
|
|
'duration': int(info.find('DURATION').text),
|
|
|
|
'upload_date': info.find('REGDTTM').text[:8],
|
|
|
|
}
|