[doodstream] add new extractor

This commit is contained in:
sxvghd 2021-01-29 19:01:36 +01:00 committed by schnusch
parent a800838f5a
commit 2b488a9179
3 changed files with 74 additions and 0 deletions

View File

@ -0,0 +1,67 @@
# coding: utf-8
from __future__ import unicode_literals
import string
import random
import time
import re
from .common import InfoExtractor
class DoodStreamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch|so)/[ed]/(?P<id>[a-z0-9]+)'
_TESTS = [{
'url': 'https://dood.to/d/wpyp2mgwi2kb',
'md5': '2aaf633bcd5fefb64b27344f55022bf9',
'info_dict': {
'id': 'wpyp2mgwi2kb',
'ext': 'mp4',
'title': 'Big Buck Bunny Trailer',
'thumbnail': r're:^https?://.*\.jpg$',
},
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?://)?dood\.(?:watch|to|so)/e/.+?)["\']',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if '/d/' in url:
url = "https://dood.to" + self._html_search_regex(
r'<iframe src="(/e/[a-z0-9]+)"', webpage, 'embed')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(['og:title', 'twitter:title'],
webpage, default=None)
thumb = self._html_search_meta(['og:image', 'twitter:image'],
webpage, default=None)
token = self._html_search_regex(r'[?&]token=([a-z0-9]+)[&\']', webpage, 'token')
description = self._html_search_meta(
['og:description', 'description', 'twitter:description'],
webpage, default=None)
auth_url = 'https://dood.to' + self._html_search_regex(
r'(/pass_md5.*?)\'', webpage, 'pass_md5')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
'referer': url
}
webpage = self._download_webpage(auth_url, video_id, headers=headers)
final_url = webpage + ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(10)) + "?token=" + token + "&expiry=" + str(int(time.time() * 1000))
return {
'id': video_id,
'title': title,
'url': final_url,
'http_headers': headers,
'ext': 'mp4',
'description': description,
'thumbnail': thumb,
}

View File

@ -308,6 +308,7 @@ from .discoverynetworks import DiscoveryNetworksDeIE
from .discoveryvr import DiscoveryVRIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .doodstream import DoodStreamIE
from .dropbox import DropboxIE
from .dw import (
DWIE,

View File

@ -129,6 +129,7 @@ from .odnoklassniki import OdnoklassnikiIE
from .kinja import KinjaEmbedIE
from .arcpublishing import ArcPublishingIE
from .medialaan import MedialaanIE
from .doodstream import DoodStreamIE
class GenericIE(InfoExtractor):
@ -3299,6 +3300,11 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
doodstream_urls = DoodStreamIE._extract_urls(webpage)
if doodstream_urls:
return self.playlist_from_matches(
doodstream_urls, video_id, video_title, ie=DoodStreamIE.ie_key())
sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
webpage)]