Merge branch 'daum' of https://github.com/remitamine/youtube-dl into remitamine-daum

This commit is contained in:
remitamine 2015-12-29 10:40:32 +01:00
commit 126d7701b0
2 changed files with 88 additions and 62 deletions

View file

@ -133,7 +133,10 @@ from .dailymotion import (
DailymotionUserIE, DailymotionUserIE,
DailymotionCloudIE, DailymotionCloudIE,
) )
from .daum import DaumIE from .daum import (
DaumIE,
DaumClipIE,
)
from .dbtv import DBTVIE from .dbtv import DBTVIE
from .dcn import ( from .dcn import (
DCNIE, DCNIE,

View file

@ -2,16 +2,81 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_urllib_parse
compat_urllib_parse, from ..utils import (
int_or_none,
str_to_int,
xpath_text,
) )
class DaumIE(InfoExtractor): class DaumIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)' _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/v/(?P<id>[^?#&]+)'
IE_NAME = 'daum.net'
_TESTS = [{
'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
'info_dict': {
'id': 'vab4dyeDBysyBssyukBUjBz',
'ext': 'mp4',
'title': '마크 헌트 vs 안토니오 실바',
'description': 'Mark Hunt vs Antonio Silva',
'upload_date': '20131217',
'duration': 2117,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
query = compat_urllib_parse.urlencode({'vid': video_id})
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
'Downloading video info')
movie_data = self._download_json(
'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
video_id, 'Downloading video formats info')
formats = []
for format_el in movie_data['output_list']['output_list']:
profile = format_el['profile']
format_query = compat_urllib_parse.urlencode({
'vid': video_id,
'profile': profile,
})
url_doc = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
video_id, note='Downloading video data for %s format' % profile)
format_url = url_doc.find('result/url').text
formats.append({
'url': format_url,
'format_id': profile,
'width': int_or_none(format_el.get('width')),
'height': int_or_none(format_el.get('height')),
'filesize': int_or_none(format_el.get('filesize')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info.find('TITLE').text,
'formats': formats,
'thumbnail': xpath_text(info, 'THUMB_URL'),
'description': xpath_text(info, 'CONTENTS'),
'duration': int_or_none(xpath_text(info, 'DURATION')),
'upload_date': info.find('REGDTTM').text[:8],
'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
}
class DaumClipIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.do|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
IE_NAME = 'daum.net' IE_NAME = 'daum.net'
_TESTS = [{ _TESTS = [{
@ -23,67 +88,25 @@ class DaumIE(InfoExtractor):
'description': 'DOTA 2GETHER 시즌2 6회 - 2부', 'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
'upload_date': '20130831', 'upload_date': '20130831',
'duration': 3868, 'duration': 3868,
'view_count': int,
}, },
}, {
# Test for https://github.com/rg3/youtube-dl/issues/7949
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=M1O35s8HPOo0&clipid=73147290',
'md5': 'c92d78bcee4424451f1667f275c1dc97',
'info_dict': {
'id': '73147290',
'ext': 'mp4',
'title': '싸이 - 나팔바지 [유희열의 스케치북] 299회 20151218',
'description': '싸이 - 나팔바지',
'upload_date': '20151219',
'duration': 232,
},
}, {
'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
'only_matching': True,
}, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id') clip_info = self._download_json(
canonical_url = 'http://tvpot.daum.net/v/%s' % video_id 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
webpage = self._download_webpage(canonical_url, video_id) video_id, 'Downloading clip info')['clip_bean']
og_url = self._og_search_url(webpage, default=None) or self._search_regex(
r'<link[^>]+rel=(["\'])canonical\1[^>]+href=(["\'])(?P<url>.+?)\2',
webpage, 'canonical url', group='url')
full_id = self._search_regex(
r'tvpot\.daum\.net/v/([^/]+)', og_url, 'full id')
query = compat_urllib_parse.urlencode({'vid': full_id})
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
'Downloading video info')
urls = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
video_id, 'Downloading video formats info')
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='Downloading video data for %s format' % profile)
format_url = url_doc.find('result/url').text
formats.append({
'url': format_url,
'format_id': profile,
})
return { return {
'_type': 'url_transparent',
'id': video_id, 'id': video_id,
'title': info.find('TITLE').text, 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
'formats': formats, 'title': clip_info['title'],
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': clip_info.get('thumb_url'),
'description': info.find('CONTENTS').text, 'description': clip_info.get('contents'),
'duration': int(info.find('DURATION').text), 'duration': int_or_none(clip_info.get('duration')),
'upload_date': info.find('REGDTTM').text[:8], 'upload_date': clip_info.get('up_date')[:8],
'view_count': int_or_none(clip_info.get('play_count')),
'ie_key': 'Daum',
} }