ytdl-nightly/youtube_dl/extractor/gorillavid.py

88 lines
2.6 KiB
Python
Raw Normal View History

2014-06-17 15:18:46 +02:00
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-06-17 15:18:46 +02:00
from ..utils import (
determine_ext,
compat_urllib_parse,
compat_urllib_request,
)
class GorillaVidIE(InfoExtractor):
IE_DESC = 'GorillaVid.in and daclips.in'
_VALID_URL = r'''(?x)
https?://(?:www\.)?
(?:daclips\.in|gorillavid\.in)/
(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
'''
2014-06-17 15:18:46 +02:00
_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',
2014-06-08 08:13:45 +02:00
'md5': 'c9e293ca74d46cad638e199c3f3fe604',
'info_dict': {
2014-06-08 08:13:45 +02:00
'id': 'z08zf8le23c6',
'ext': 'mp4',
'title': 'Say something nice',
2014-06-17 15:18:46 +02:00
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://daclips.in/3rso4kdn6f9m',
'info_dict': {
'id': '3rso4kdn6f9m',
'ext': 'mp4',
'title': 'Micro Pig piglets ready on 16th July 2009',
'thumbnail': 're:http://.*\.jpg',
},
2014-06-17 15:18:46 +02:00
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
2014-06-17 15:18:46 +02:00
fields = dict(re.findall(r'''(?x)<input\s+
type="hidden"\s+
name="([^"]+)"\s+
(?:id="[^"]+"\s+)?
value="([^"]*)"
''', webpage))
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')
2014-06-17 15:18:46 +02:00
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,
'title': title,
2014-06-17 15:18:46 +02:00
'thumbnail': thumbnail,
'formats': formats,
}