dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[dotsub] Fix extraction and modernize

This commit is contained in:
Sergey M․ 2015-02-11 22:33:03 +06:00
parent d304209a85
commit 124f3bc67d
1 changed files with 27 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
youtube_dl/extractor/dotsub.py
View File

@ -1,13 +1,14 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
)
class DotsubIE(InfoExtractor): class DotsubIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
_TEST = { _TEST = {
'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27', 'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'md5': '0914d4d69605090f623b7ac329fea66e', 'md5': '0914d4d69605090f623b7ac329fea66e',
@ -15,28 +16,37 @@ class DotsubIE(InfoExtractor):
'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27', 'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'ext': 'flv', 'ext': 'flv',
'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary', 'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
'duration': 3169,
'uploader': '4v4l0n42', 'uploader': '4v4l0n42',
'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com', 'timestamp': 1292248482.625,
'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
'upload_date': '20101213', 'upload_date': '20101213',
'view_count': int,
} }
} }
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')
info_url = "https://dotsub.com/api/media/%s/metadata" % video_id info = self._download_json(
info = self._download_json(info_url, video_id) 'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
date = time.gmtime(info['dateCreated'] / 1000) # The timestamp is in miliseconds video_url = info.get('mediaURI')
if not video_url:
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
return { return {
'id': video_id, 'id': video_id,
'url': info['mediaURI'], 'url': video_url,
'ext': 'flv', 'ext': 'flv',
'title': info['title'], 'title': info['title'],
'thumbnail': info['screenshotURI'], 'description': info.get('description'),
'description': info['description'], 'thumbnail': info.get('screenshotURI'),
'uploader': info['user'], 'duration': int_or_none(info.get('duration'), 1000),
'view_count': info['numberOfViews'], 'uploader': info.get('user'),
'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday), 'timestamp': float_or_none(info.get('dateCreated'), 1000),
'view_count': int_or_none(info.get('numberOfViews')),
} }