Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

[allmyvideos] Support multiple formats

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-09-16 22:56:31 +02:00
parent 7cdd5339b3
commit e825c38082
1 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/allmyvideos.py
View File

@ -1,6 +1,7 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import os.path
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -16,7 +17,7 @@ class AllmyvideosIE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://allmyvideos.net/jih3nce3x6wn', 'url': 'http://allmyvideos.net/jih3nce3x6wn',
'md5': '8f26c1e7102556a0d7f24306d32c2092', 'md5': '710883dee1bfc370ecf9fa6a89307c88',
'info_dict': { 'info_dict': {
'id': 'jih3nce3x6wn', 'id': 'jih3nce3x6wn',
'ext': 'mp4', 'ext': 'mp4',
@ -30,22 +31,29 @@ def _real_extract(self, url):
orig_webpage = self._download_webpage(url, video_id) orig_webpage = self._download_webpage(url, video_id)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = {} data = dict(fields)
for name, value in fields:
data[name] = value
post = compat_urllib_parse.urlencode(data) post = compat_urllib_parse.urlencode(data)
headers = { headers = {
b'Content-Type': b'application/x-www-form-urlencoded', b'Content-Type': b'application/x-www-form-urlencoded',
} }
req = compat_urllib_request.Request(url, post, headers) req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(req, video_id, note='Downloading video page ...') webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
#Could be several links with different quality #Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage) links = re.findall(r'"file" : "?(.+?)",', webpage)
# Assume the links are ordered in quality
formats = [{
'url': l,
'quality': i,
} for i, l in enumerate(links)]
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': data['fname'][:len(data['fname'])-4], #Remove .mp4 extension 'title': title,
'url': links[len(links)-1] #Choose the higher quality link 'formats': formats,
} }