Ir90Tv Add new extractor

This commit is contained in:
Behrooz 2015-05-08 02:50:46 +02:00
parent 7ef00afe9d
commit a745475808
2 changed files with 42 additions and 0 deletions

View file

@ -229,6 +229,7 @@ from .infoq import InfoQIE
from .instagram import InstagramIE, InstagramUserIE
from .internetvideoarchive import InternetVideoArchiveIE
from .iprima import IPrimaIE
from .ir90tv import Ir90TvIE
from .ivi import (
IviIE,
IviCompilationIE

View file

@ -0,0 +1,41 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class Ir90TvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?90tv\.ir/video/(?P<id>[0-9]+)/.*'
_TEST = {
'url': 'http://90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
'md5': '411dbd94891381960cb9e13daa47a869',
'info_dict': {
'id': '95719',
'ext': 'mp4',
'title': 'شایعات نقل و انتقالات مهم فوتبال اروپا 94/02/18',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(
r'<title>\n90tv.ir :: (.*?)</title>', webpage, 'title')
video_url = self._search_regex(
r'<source[^>]+src="([^"]+)"', webpage, 'video url')
thumbnail = self._search_regex(r'poster="([^"]+)"', webpage, 'thumbnail url')
print thumbnail
return {
'url': video_url,
'id': video_id,
'title': title,
'video_url' : video_url,
'thumbnail' : thumbnail,
}