[GorillaVid] improve extractor

This commit is contained in:
Petr Půlpán 2014-06-17 15:18:46 +02:00
parent 25e9953c6f
commit 5f28a1acad
1 changed files with 53 additions and 15 deletions

View File

@ -1,38 +1,76 @@
# coding: utf-8 # -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
determine_ext,
compat_urllib_parse,
compat_urllib_request,
)
class GorillaVidIE(InfoExtractor): class GorillaVidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?gorillavid.in/(?:embed-)?(?P<id>\w+)(?:\-\d+x\d+)?(?:.html)?' _VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
_TEST = {
'url': "http://gorillavid.in/z08zf8le23c6", _TESTS = [{
'url': 'http://gorillavid.in/06y9juieqpmi',
'md5': '5ae4a3580620380619678ee4875893ba',
'info_dict': {
'id': '06y9juieqpmi',
'ext': 'flv',
'title': 'Rebecca Black My Moment Official Music Video Reaction',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
'md5': 'c9e293ca74d46cad638e199c3f3fe604', 'md5': 'c9e293ca74d46cad638e199c3f3fe604',
'info_dict': { 'info_dict': {
'id': 'z08zf8le23c6', 'id': 'z08zf8le23c6',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Say something nice', 'title': 'Say something nice',
} 'thumbnail': 're:http://.*\.jpg',
} },
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
url = 'http://gorillavid.in/%s' % video_id
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r"name=['\"]fname['\"]\s+value=['\"](.*?)['\"]", webpage, u"video title")
# download embed page again with cookies to get url fields = dict(re.findall(r'''(?x)<input\s+
embed_url = "http://gorillavid.in/embed-{0}-960x480.html".format(video_id) type="hidden"\s+
webpage = self._download_webpage(embed_url, video_id, note=u'Downloading webpage again (with cookie)') name="([^"]+)"\s+
url = self._html_search_regex(r'file:\s+["\'](http://.*?video.\w{3})["\']', webpage, url) (?:id="[^"]+"\s+)?
value="([^"]*)"
''', webpage))
info_dict = { if fields['op'] == 'download1':
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
formats = [{
'format_id': 'sd',
'url': url,
'ext': determine_ext(url),
'quality': 1,
}]
return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': url, 'thumbnail': thumbnail,
'formats': formats,
} }
return info_dict