aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-01-03 12:20:18 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-01-03 12:20:18 +0100
commitd2fee313ec71ad8a4d8b57ec9f433210ee01056b (patch)
tree77345b74e30d98c6d9df59610ff8d3cf15945121
parentfa7f58e43380e3c7c556db52c63d436d5f8db3ef (diff)
parent4a9c9b6fdba3782e6342d43769d5dd777797d640 (diff)
Merge remote-tracking branch 'diffycat/jpopsuki'
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/jpopsukitv.py65
2 files changed, 66 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5319a9292..9c1374373 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -95,6 +95,7 @@ from .ivi import (
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
+from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .keezmovies import KeezMoviesIE
from .kickstarter import KickStarterIE
diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py
new file mode 100644
index 000000000..5e8f91d51
--- /dev/null
+++ b/youtube_dl/extractor/jpopsukitv.py
@@ -0,0 +1,65 @@
+# coding=utf-8
+import re
+from ..utils import unified_strdate
+from .common import InfoExtractor
+
+
+class JpopsukiIE(InfoExtractor):
+ IE_NAME = u'jpopsuki.tv'
+ _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
+
+ _TEST = {
+ u'url': u'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
+ u'md5': u'88018c0c1a9b1387940e90ec9e7e198e',
+ u'file': u'00be659d23b0b40508169cdee4545771.mp4',
+ u'info_dict': {
+ u'id': u'00be659d23b0b40508169cdee4545771',
+ u'title': u'ayumi hamasaki - evolution',
+ 'description': u'Release date: 2001.01.31\r 浜崎あゆみ - evolution',
+ 'thumbnail': u'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
+ 'uploader': u'plama_chan',
+ 'uploader_id': u'404',
+ 'upload_date': u'20121101'
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
+ r'<source src="(.*?)" type', webpage, u'video url')
+
+ video_title = self._html_search_regex(
+ r'<meta name="og:title" content="(.*?)" />', webpage, u'video title')
+ description = self._html_search_regex(
+ r'<meta name="og:description" content="(.*?)" />', webpage, u'video description', flags=re.DOTALL)
+ thumbnail = self._html_search_regex(
+ r'<meta name="og:image" content="(.*?)" />', webpage, u'video thumbnail')
+ uploader = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/(.*?)/uid/', webpage, u'video uploader')
+ uploader_id = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', webpage, u'video uploader_id')
+ upload_date = self._html_search_regex(
+ r'<li>uploaded: (.*?)</li>', webpage, u'video upload_date')
+ if upload_date is not None:
+ upload_date = unified_strdate(upload_date)
+ view_count = self._html_search_regex(
+ r'<li>Hits: (\d*?)</li>', webpage, u'video view_count')
+ comment_count = self._html_search_regex(
+ r'<h2>(\d*?) comments</h2>', webpage, u'video comment_count')
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'upload_date': upload_date,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ } \ No newline at end of file