MarcoBuster/youtube-dl
1
1
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-27 04:26:50 +01:00
Code Issues Releases Wiki Activity

[internetvideoarchive] fix extraction

Browse Source
This commit is contained in:
Remita Amine 2019-10-28 19:45:42 +01:00
parent 895e5c03db
commit 83e49259bf
1 changed files with 28 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

92
youtube_dl/extractor/internetvideoarchive.py
View File

@ -1,15 +1,13 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_parse_qs, compat_parse_qs,
compat_urlparse, compat_urlparse,
) )
from ..utils import (
determine_ext,
int_or_none,
xpath_text,
)
class InternetVideoArchiveIE(InfoExtractor): class InternetVideoArchiveIE(InfoExtractor):
@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '194487', 'id': '194487',
'ext': 'mp4', 'ext': 'mp4',
'title': 'KICK-ASS 2', 'title': 'Kick-Ass 2',
'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
}, },
'params': { 'params': {
@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor):
def _build_json_url(query): def _build_json_url(query):
return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query
@staticmethod
def _build_xml_url(query):
return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query
def _real_extract(self, url): def _real_extract(self, url):
query = compat_urlparse.urlparse(url).query query = compat_parse_qs(compat_urlparse.urlparse(url).query)
query_dic = compat_parse_qs(query) video_id = query['publishedid'][0]
video_id = query_dic['publishedid'][0] data = self._download_json(
'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx',
if '/player/' in url: video_id, data=json.dumps({
configuration = self._download_json(url, video_id) 'customerid': query['customerid'][0],
'publishedid': video_id,
# There are multiple videos in the playlist whlie only the first one }).encode())
# matches the video played in browsers title = data['Title']
video_info = configuration['playlist'][0] formats = self._extract_m3u8_formats(
title = video_info['title'] data['VideoUrl'], video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
formats = [] file_url = formats[0]['url']
for source in video_info['sources']: if '.ism/' in file_url:
file_url = source['file'] replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url)
if determine_ext(file_url) == 'm3u8': formats.extend(self._extract_f4m_formats(
m3u8_formats = self._extract_m3u8_formats( replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) formats.extend(self._extract_mpd_formats(
if m3u8_formats: replace_url('.mpd'), video_id, mpd_id='dash', fatal=False))
formats.extend(m3u8_formats) formats.extend(self._extract_ism_formats(
file_url = m3u8_formats[0]['url'] replace_url('Manifest'), video_id, ism_id='mss', fatal=False))
formats.extend(self._extract_f4m_formats( self._sort_formats(formats)
file_url.replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
file_url.replace('.m3u8', '.mpd'),
video_id, mpd_id='dash', fatal=False))
else:
a_format = {
'url': file_url,
}
if source.get('label') and source['label'][-4:] == ' kbs':
tbr = int_or_none(source['label'][:-4])
a_format.update({
'tbr': tbr,
'format_id': 'http-%d' % tbr,
})
formats.append(a_format)
self._sort_formats(formats)
description = video_info.get('description')
thumbnail = video_info.get('image')
else:
configuration = self._download_xml(url, video_id)
formats = [{
'url': xpath_text(configuration, './file', 'file URL', fatal=True),
}]
thumbnail = xpath_text(configuration, './image', 'thumbnail')
title = 'InternetVideoArchive video %s' % video_id
description = None
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': data.get('PosterUrl'),
'description': description, 'description': data.get('Description'),
} }