depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 11:41:52 +00:00
Code Issues Releases Wiki Activity

[dump] Modernize (#3565)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-08-22 01:43:19 +02:00
parent a200f4cee2
commit 91dff03217
1 changed files with 12 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
youtube_dl/extractor/dump.py
View file

@ -4,19 +4,19 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class DumpIE(InfoExtractor): class DumpIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
_TEST = { _TEST = {
u'url': u'http://www.dump.com/oneus/', 'url': 'http://www.dump.com/oneus/',
u'file': u'oneus.flv', 'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99',
u'md5': u'ad71704d1e67dfd9e81e3e8b42d69d99', 'info_dict': {
u'info_dict': { 'id': 'oneus',
u"title": u"He's one of us.", 'ext': 'flv',
'title': "He's one of us.",
'thumbnail': 're:^https?://.*\.jpg$',
}, },
} }
@ -24,25 +24,16 @@ class DumpIE(InfoExtractor):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
video_id = m.group('id') video_id = m.group('id')
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
try: thumb = self._og_search_thumbnail(webpage)
video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1] title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
except IndexError:
raise ExtractorError(u'No video URL found')
thumb = re.findall('<meta property="og:image" content="(.+?)"',webpage)[0]
title = self._search_regex(r'<b>([^"]+)</b>', webpage, u'title')
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
'ext': 'flv',
'thumbnail': thumb, 'thumbnail': thumb,
} }