aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/daum.py
diff options
context:
space:
mode:
authorremitamine <remitamine@gmail.com>2015-12-29 10:40:32 +0100
committerremitamine <remitamine@gmail.com>2015-12-29 10:40:32 +0100
commit126d7701b0f88c33b5fbda6fd07ef056b96c9367 (patch)
tree439ff731a0c47eb7c3907b6409cc5c94d1e41e0d /youtube_dl/extractor/daum.py
parentecf17d165317078d0e31191e40903a74fc3da3e8 (diff)
parent720334659ac13d7f5bc0759662ba0534f48a1ce4 (diff)
Merge branch 'daum' of https://github.com/remitamine/youtube-dl into remitamine-daum
Diffstat (limited to 'youtube_dl/extractor/daum.py')
-rw-r--r--youtube_dl/extractor/daum.py111
1 files changed, 67 insertions, 44 deletions
diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index 9a94cf361..a083cc0dc 100644
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -2,71 +2,51 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..compat import (
- compat_urllib_parse,
+from ..compat import compat_urllib_parse
+from ..utils import (
+ int_or_none,
+ str_to_int,
+ xpath_text,
)
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/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,
- },
- }, {
- # Test for https://github.com/rg3/youtube-dl/issues/7949
- 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=M1O35s8HPOo0&clipid=73147290',
- 'md5': 'c92d78bcee4424451f1667f275c1dc97',
+ 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
'info_dict': {
- 'id': '73147290',
+ 'id': 'vab4dyeDBysyBssyukBUjBz',
'ext': 'mp4',
- 'title': '싸이 - 나팔바지 [유희열의 스케치북] 299회 20151218',
- 'description': '싸이 - 나팔바지',
- 'upload_date': '20151219',
- 'duration': 232,
+ '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/vab4dyeDBysyBssyukBUjBz',
- 'only_matching': True,
- }, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
- webpage = self._download_webpage(canonical_url, video_id)
- 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})
+ 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')
- urls = self._download_xml(
- 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
+ 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 urls.findall('result/output_list/output_list'):
- profile = format_el.attrib['profile']
+ for format_el in movie_data['output_list']['output_list']:
+ profile = format_el['profile']
format_query = compat_urllib_parse.urlencode({
- 'vid': full_id,
+ 'vid': video_id,
'profile': profile,
})
url_doc = self._download_xml(
@@ -76,14 +56,57 @@ class DaumIE(InfoExtractor):
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': self._og_search_thumbnail(webpage),
- 'description': info.find('CONTENTS').text,
- 'duration': int(info.find('DURATION').text),
+ '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'
+
+ _TESTS = [{
+ '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,
+ 'view_count': int,
+ },
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ clip_info = self._download_json(
+ 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
+ video_id, 'Downloading clip info')['clip_bean']
+
+ return {
+ '_type': 'url_transparent',
+ 'id': video_id,
+ 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
+ 'title': clip_info['title'],
+ 'thumbnail': clip_info.get('thumb_url'),
+ 'description': clip_info.get('contents'),
+ 'duration': int_or_none(clip_info.get('duration')),
+ 'upload_date': clip_info.get('up_date')[:8],
+ 'view_count': int_or_none(clip_info.get('play_count')),
+ 'ie_key': 'Daum',
}