2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 15:52:38 +00:00
yt-dlp/youtube_dl/extractor/daum.py

71 lines
2.5 KiB
Python
Raw Normal View History

# encoding: utf-8
2014-03-21 13:03:18 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class DaumIE(InfoExtractor):
2013-12-12 12:05:38 +00:00
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
2014-03-21 13:03:18 +00:00
IE_NAME = 'daum.net'
_TEST = {
2014-03-21 13:03:18 +00:00
'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
'info_dict': {
'id': '52554690',
'ext': 'mp4',
'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
'upload_date': '20130831',
'duration': 3868,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
webpage = self._download_webpage(canonical_url, video_id)
2013-12-03 13:16:58 +00:00
full_id = self._search_regex(
r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
2014-03-21 13:03:18 +00:00
webpage, 'full id')
query = compat_urllib_parse.urlencode({'vid': full_id})
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
2014-03-21 13:03:18 +00:00
'Downloading video info')
urls = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
2014-03-21 13:03:18 +00:00
video_id, '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,
})
url_doc = self._download_xml(
'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,
'format_id': profile,
})
return {
'id': video_id,
'title': info.find('TITLE').text,
'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'description': info.find('CONTENTS').text,
'duration': int(info.find('DURATION').text),
'upload_date': info.find('REGDTTM').text[:8],
}