[news18] Add new extractor

This commit is contained in:
Ashwin Dhakaita 2018-11-04 10:13:07 +05:30
parent 3819e62a61
commit 8b85d2d019
1 changed files with 5 additions and 8 deletions

View File

@ -1,14 +1,13 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class News18IE(InfoExtractor):
_VALID_URL = r'''https?:\/\/www\.news18\.com[a-zA-Z0-9_\/-]+-(?P<id>\d+)\.html'''
_TEST = {
'url' : 'https://www.news18.com/news/ivideos/inside-naxal-bastion-news18-visits-the-villages-voting-first-time-ever-1928149.html',
'md5' : 'cb5a78310f3e583da5ba0de38b450938',
'url': 'https://www.news18.com/news/ivideos/inside-naxal-bastion-news18-visits-the-villages-voting-first-time-ever-1928149.html',
'md5': 'cb5a78310f3e583da5ba0de38b450938',
'info_dict': {
'id': '1928149',
'ext': 'mp4',
@ -17,10 +16,9 @@ class News18IE(InfoExtractor):
}
def _real_extract(self, url):
IE_NAME = 'News18'
video_id = self._match_id(url)
webpage = self._download_webpage(url,video_id)
video_url = self._search_regex(r'(?P<url>https?:\/\/vodpd\.news18\.com[\/\w_-]+\.mp4)', webpage, 'video URL',default='')
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(r'(?P<url>https?:\/\/vodpd\.news18\.com[\/\w_-]+\.mp4)', webpage, 'video URL', default='')
title = self._og_search_title(webpage)
return {
@ -29,4 +27,3 @@ class News18IE(InfoExtractor):
'title': title,
'ext': 'mp4'
}