Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-15 04:09:59 +08:00
Code Issues Releases Wiki Activity

generalise regex for other url formats also, and return all possible video formats instead of just 360p

Browse Source
This commit is contained in:
Abhishek Kedia 2015-12-20 23:51:00 +01:00
parent 826c5473c1
commit c5c2d9c1e9
1 changed files with 14 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
youtube_dl/extractor/genvideos.py
View File

@ -4,35 +4,24 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
import requests import requests
import json
import urllib import urllib
from urlparse import parse_qs, urlparse from urlparse import parse_qs, urlparse
class GenVideosIE(InfoExtractor): class GenVideosIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?genvideos.org/watch\?v=(?P<id>\w+)#?' #Tests only the basic url format. Example - https://genvideos.org/watch?v=kMjlhMWE5OT _VALID_URL = r'https?://(?:www\.)?genvideos.(org|com)/watch(\?v=|_)(?P<id>\w+)#?'
# TODO check for other possible url formats also
# For example
# * http://genvideos.com/watch_kMjlhMWE5OT.html#video=tBa-Q-WkbPqwzs34b7ArqU7VomQMb2n-RAlARWKWKTI
# * http://genvideos.org/watch_kMjlhMWE5OT.html#video=tBa-Q-WkbPqwzs34b7ArqU7VomQMb2n-RAlARWKWKTI
_TESTS = [{ _TESTS = [{
'url': 'http://genvideos.org/watch?v=kMjlhMWE5OT', 'url': 'http://genvideos.org/watch?v=kMjlhMWE5OT',
'md5': '666118ec1176f14259bb9f11c74bea83', 'md5': 'f610bd838c21c083ede8a05ca18d55e2', #1080p quality
'info_dict': { 'info_dict': {
'id': 'kMjlhMWE5OT', 'id': 'kMjlhMWE5OT',
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Hunger Games (2012) - HD 1080p', 'title': 'The Hunger Games (2012) - HD 1080p',
'description': 'In a dystopian future, the totalitarian nation of Panem is divided between 12 districts and the Capitol. Each year two young representatives from each distri...' 'description': 'In a dystopian future, the totalitarian nation of Panem is divided between 12 districts and the Capitol. Each year two young representatives from each distri...'
#'thumbnail': 're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
}, { }, {
'url': 'https://genvideos.org/watch?v=Pitch_Perfect_2_2015#video=tBa-Q-WkbPqwzs34b7ArqU7VomQMb2n-RAlARWKWKTI', 'url': 'https://genvideos.org/watch?v=Pitch_Perfect_2_2015#video=tBa-Q-WkbPqwzs34b7ArqU7VomQMb2n-RAlARWKWKTI',
'md5': '441b5c9f0445724b0f6f9d6e5498e577', 'md5': 'df4011514016747ea3478d1776ffece2', #1080p quality
'info_dict':{ 'info_dict':{
'id': 'Pitch_Perfect_2_2015', 'id': 'Pitch_Perfect_2_2015',
'ext': 'mp4', 'ext': 'mp4',
@ -46,24 +35,23 @@ class GenVideosIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title') title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
#TODO retrieve video url #TODO retrieve video url (using requests dependency for the moment)
urls_data = requests.post( urls_data = requests.post(
"https://genvideos.org/video_info/iframe", "https://genvideos.org/video_info/iframe",
data={'v':video_id}, data={'v':video_id},
headers={'referer': 'https://genvideos.org/'} headers={'referer': 'https://genvideos.org/'}
) #returns json containing the url of the video (in 360p, 720p and 1080p). ) #returns json containing the url of the video (in 360p, 720p and 1080p). For example - {"360":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm18","720":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm22","1080":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm37"}
#For example - {"360":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm18","720":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm22","1080":"\/\/html5player.org\/embed?url=https%3A%2F%2Flh3.googleusercontent.com%2FW6-SNGaDLWNyucD3pMqa1uMBapGDbtMTOtwpXrEu-w%3Dm37"} urls_data_json = self._parse_json(urls_data.text,video_id)
urls_data_json = json.loads(urls_data.text) formats = []
_360p_url = parse_qs(urlparse(urls_data_json['360']).query)['url'][0] for quality in sorted(urls_data_json,key=lambda q:int(q)):
#_360p_url = urllib.urlopen(_360p_redirect_url).geturl() formats.append({
# TODO : return all possible formats instead of just 360p 'url':parse_qs(urlparse(urls_data_json[quality]).query)['url'][0],
'ext':'mp4',
'format_id':quality
})
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': _360p_url,
'ext': 'mp4',
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
#'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), 'formats':formats
# TODO more properties (see youtube_dl/extractor/common.py)
} }