[gorillavid] Generalize extraction with countdown timeout and support faststream.in (Closes #4297)

This commit is contained in:
Sergey M․ 2014-11-26 20:02:40 +06:00
parent a03aaaed2e
commit ceb3367320

View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor
from ..utils import (
@ -9,6 +10,7 @@
determine_ext,
compat_urllib_parse,
compat_urllib_request,
int_or_none,
)
@ -16,7 +18,7 @@ class GorillaVidIE(InfoExtractor):
IE_DESC = 'GorillaVid.in, daclips.in and movpod.in'
_VALID_URL = r'''(?x)
https?://(?P<host>(?:www\.)?
(?:daclips\.in|gorillavid\.in|movpod\.in))/
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
'''
@ -49,6 +51,16 @@ class GorillaVidIE(InfoExtractor):
'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
'thumbnail': 're:http://.*\.jpg',
}
}, {
# video with countdown timeout
'url': 'http://fastvideo.in/1qmdn1lmsmbw',
'md5': '8b87ec3f6564a3108a0e8e66594842ba',
'info_dict': {
'id': '1qmdn1lmsmbw',
'ext': 'mp4',
'title': 'Man of Steel - Trailer',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'only_matching': True,
@ -71,6 +83,12 @@ def _real_extract(self, url):
''', webpage))
if fields['op'] == 'download1':
countdown = int_or_none(self._search_regex(
r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
webpage, 'countdown', default=None))
if countdown:
self._sleep(countdown, video_id)
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
@ -78,9 +96,13 @@ def _real_extract(self, url):
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = self._search_regex(r'style="z-index: [0-9]+;">([^<]+)</span>', webpage, 'title')
video_url = self._search_regex(r'file\s*:\s*\'(http[^\']+)\',', webpage, 'file url')
thumbnail = self._search_regex(r'image\s*:\s*\'(http[^\']+)\',', webpage, 'thumbnail', fatal=False)
title = self._search_regex(
r'style="z-index: [0-9]+;">([^<]+)</span>',
webpage, 'title', default=None) or self._og_search_title(webpage)
video_url = self._search_regex(
r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
thumbnail = self._search_regex(
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
formats = [{
'format_id': 'sd',