1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-30 20:45:52 +01:00
youtube-dl/youtube_dl/extractor/sandia.py
Sergey M? 5c2266df4b Switch codebase to use sanitized_Request instead of
compat_urllib_request.Request

[downloader/dash] Use sanitized_Request

[downloader/http] Use sanitized_Request

[atresplayer] Use sanitized_Request

[bambuser] Use sanitized_Request

[bliptv] Use sanitized_Request

[brightcove] Use sanitized_Request

[cbs] Use sanitized_Request

[ceskatelevize] Use sanitized_Request

[collegerama] Use sanitized_Request

[extractor/common] Use sanitized_Request

[crunchyroll] Use sanitized_Request

[dailymotion] Use sanitized_Request

[dcn] Use sanitized_Request

[dramafever] Use sanitized_Request

[dumpert] Use sanitized_Request

[eitb] Use sanitized_Request

[escapist] Use sanitized_Request

[everyonesmixtape] Use sanitized_Request

[extremetube] Use sanitized_Request

[facebook] Use sanitized_Request

[fc2] Use sanitized_Request

[flickr] Use sanitized_Request

[4tube] Use sanitized_Request

[gdcvault] Use sanitized_Request

[extractor/generic] Use sanitized_Request

[hearthisat] Use sanitized_Request

[hotnewhiphop] Use sanitized_Request

[hypem] Use sanitized_Request

[iprima] Use sanitized_Request

[ivi] Use sanitized_Request

[keezmovies] Use sanitized_Request

[letv] Use sanitized_Request

[lynda] Use sanitized_Request

[metacafe] Use sanitized_Request

[minhateca] Use sanitized_Request

[miomio] Use sanitized_Request

[meovideo] Use sanitized_Request

[mofosex] Use sanitized_Request

[moniker] Use sanitized_Request

[mooshare] Use sanitized_Request

[movieclips] Use sanitized_Request

[mtv] Use sanitized_Request

[myvideo] Use sanitized_Request

[neteasemusic] Use sanitized_Request

[nfb] Use sanitized_Request

[niconico] Use sanitized_Request

[noco] Use sanitized_Request

[nosvideo] Use sanitized_Request

[novamov] Use sanitized_Request

[nowness] Use sanitized_Request

[nuvid] Use sanitized_Request

[played] Use sanitized_Request

[pluralsight] Use sanitized_Request

[pornhub] Use sanitized_Request

[pornotube] Use sanitized_Request

[primesharetv] Use sanitized_Request

[promptfile] Use sanitized_Request

[qqmusic] Use sanitized_Request

[rtve] Use sanitized_Request

[safari] Use sanitized_Request

[sandia] Use sanitized_Request

[shared] Use sanitized_Request

[sharesix] Use sanitized_Request

[sina] Use sanitized_Request

[smotri] Use sanitized_Request

[sohu] Use sanitized_Request

[spankwire] Use sanitized_Request

[sportdeutschland] Use sanitized_Request

[streamcloud] Use sanitized_Request

[streamcz] Use sanitized_Request

[tapely] Use sanitized_Request

[tube8] Use sanitized_Request

[tubitv] Use sanitized_Request

[twitch] Use sanitized_Request

[twitter] Use sanitized_Request

[udemy] Use sanitized_Request

[vbox7] Use sanitized_Request

[veoh] Use sanitized_Request

[vessel] Use sanitized_Request

[vevo] Use sanitized_Request

[viddler] Use sanitized_Request

[videomega] Use sanitized_Request

[viewvster] Use sanitized_Request

[viki] Use sanitized_Request

[vk] Use sanitized_Request

[vodlocker] Use sanitized_Request

[voicerepublic] Use sanitized_Request

[wistia] Use sanitized_Request

[xfileshare] Use sanitized_Request

[xtube] Use sanitized_Request

[xvideos] Use sanitized_Request

[yandexmusic] Use sanitized_Request

[youku] Use sanitized_Request

[youporn] Use sanitized_Request

[youtube] Use sanitized_Request

[patreon] Use sanitized_Request

[extractor/common] Remove unused import

[nfb] PEP 8
2015-11-23 21:56:23 +06:00

116 lines
4.0 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import itertools
import json
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
js_to_json,
mimetype2ext,
sanitized_Request,
unified_strdate,
)
class SandiaIE(InfoExtractor):
IE_DESC = 'Sandia National Laboratories'
_VALID_URL = r'https?://digitalops\.sandia\.gov/Mediasite/Play/(?P<id>[0-9a-f]+)'
_TEST = {
'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d',
'md5': '9422edc9b9a60151727e4b6d8bef393d',
'info_dict': {
'id': '24aace4429fc450fb5b38cdbf424a66e1d',
'ext': 'mp4',
'title': 'Xyce Software Training - Section 1',
'description': 're:(?s)SAND Number: SAND 2013-7800.{200,}',
'upload_date': '20120904',
'duration': 7794,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'MediasitePlayerCaps=ClientPlugins=4')
webpage = self._download_webpage(req, video_id)
js_path = self._search_regex(
r'<script type="text/javascript" src="(/Mediasite/FileServer/Presentation/[^"]+)"',
webpage, 'JS code URL')
js_url = compat_urlparse.urljoin(url, js_path)
js_code = self._download_webpage(
js_url, video_id, note='Downloading player')
def extract_str(key, **args):
return self._search_regex(
r'Mediasite\.PlaybackManifest\.%s\s*=\s*(.+);\s*?\n' % re.escape(key),
js_code, key, **args)
def extract_data(key, **args):
data_json = extract_str(key, **args)
if data_json is None:
return data_json
return self._parse_json(
data_json, video_id, transform_source=js_to_json)
formats = []
for i in itertools.count():
fd = extract_data('VideoUrls[%d]' % i, default=None)
if fd is None:
break
formats.append({
'format_id': '%s' % i,
'format_note': fd['MimeType'].partition('/')[2],
'ext': mimetype2ext(fd['MimeType']),
'url': fd['Location'],
'protocol': 'f4m' if fd['MimeType'] == 'video/x-mp4-fragmented' else None,
})
self._sort_formats(formats)
slide_baseurl = compat_urlparse.urljoin(
url, extract_data('SlideBaseUrl'))
slide_template = slide_baseurl + re.sub(
r'\{0:D?([0-9+])\}', r'%0\1d', extract_data('SlideImageFileNameTemplate'))
slides = []
last_slide_time = 0
for i in itertools.count(1):
sd = extract_str('Slides[%d]' % i, default=None)
if sd is None:
break
timestamp = int_or_none(self._search_regex(
r'^Mediasite\.PlaybackManifest\.CreateSlide\("[^"]*"\s*,\s*([0-9]+),',
sd, 'slide %s timestamp' % i, fatal=False))
slides.append({
'url': slide_template % i,
'duration': timestamp - last_slide_time,
})
last_slide_time = timestamp
formats.append({
'format_id': 'slides',
'protocol': 'slideshow',
'url': json.dumps(slides),
'preference': -10000, # Downloader not yet written
})
self._sort_formats(formats)
title = extract_data('Title')
description = extract_data('Description', fatal=False)
duration = int_or_none(extract_data(
'Duration', fatal=False), scale=1000)
upload_date = unified_strdate(extract_data('AirDate', fatal=False))
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'upload_date': upload_date,
'duration': duration,
}