aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-05 10:53:40 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-05 10:53:40 +0200
commit6b95b065be2ac6d1089968a673e3f142157f111f (patch)
tree39324c1b23a0a58a93ba3622762a24294d5c0573 /youtube_dl
parent9363169b67a7837bdd157939a896bd38b350f634 (diff)
Add extractor for tvcast.naver.com (closes #1331)
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/naver.py73
2 files changed, 74 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index caef53b73..70ebd29e2 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -58,6 +58,7 @@ from .mtv import MTVIE
from .muzu import MuzuTVIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
+from .naver import NaverIE
from .nba import NBAIE
from .nbc import NBCNewsIE
from .ooyala import OoyalaIE
diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py
new file mode 100644
index 000000000..9df236d69
--- /dev/null
+++ b/youtube_dl/extractor/naver.py
@@ -0,0 +1,73 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+ ExtractorError,
+)
+
+
+class NaverIE(InfoExtractor):
+ _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://tvcast.naver.com/v/81652',
+ u'file': u'81652.mp4',
+ u'info_dict': {
+ u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
+ u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
+ u'upload_date': u'20130903',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+ webpage = self._download_webpage(url, video_id)
+ m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
+ webpage)
+ if m_id is None:
+ raise ExtractorError(u'couldn\'t extract vid and key')
+ vid = m_id.group(1)
+ key = m_id.group(2)
+ query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
+ query_urls = compat_urllib_parse.urlencode({
+ 'masterVid': vid,
+ 'protocol': 'p2p',
+ 'inKey': key,
+ })
+ info_xml = self._download_webpage(
+ 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
+ video_id, u'Downloading video info')
+ urls_xml = self._download_webpage(
+ 'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
+ video_id, u'Downloading video formats info')
+ info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+ urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+
+ formats = []
+ for format_el in urls.findall('EncodingOptions/EncodingOption'):
+ domain = format_el.find('Domain').text
+ if domain.startswith('rtmp'):
+ continue
+ formats.append({
+ 'url': domain + format_el.find('uri').text,
+ 'ext': 'mp4',
+ 'width': int(format_el.find('width').text),
+ 'height': int(format_el.find('height').text),
+ })
+
+ info = {
+ 'id': video_id,
+ 'title': info.find('Subject').text,
+ 'formats': formats,
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'upload_date': info.find('WriteDate').text.replace('.', ''),
+ 'view_count': int(info.find('PlayCount').text),
+ }
+ # TODO: Remove when #980 has been merged
+ info.update(formats[-1])
+ return info