1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 00:17:43 +00:00
youtube-dl/youtube_dl/extractor/steam.py

150 lines
5.5 KiB
Python
Raw Normal View History

2014-04-19 17:51:04 +00:00
from __future__ import unicode_literals
2013-06-23 20:02:56 +00:00
import re
from .common import InfoExtractor
from ..utils import (
2017-10-11 17:49:48 +00:00
extract_attributes,
2013-06-23 20:02:56 +00:00
ExtractorError,
2017-10-11 17:49:48 +00:00
get_element_by_class,
js_to_json,
2013-06-23 20:02:56 +00:00
)
class SteamIE(InfoExtractor):
_VALID_URL = r"""(?x)
https?://store\.steampowered\.com/
(agecheck/)?
(?P<urltype>video|app)/ #If the page is only for videos or for a game
(?P<gameID>\d+)/?
(?P<videoID>\d*)(?P<extra>\??) # For urltype == video we sometimes get the videoID
|
https?://(?:www\.)?steamcommunity\.com/sharedfiles/filedetails/\?id=(?P<fileID>[0-9]+)
"""
2013-06-23 20:02:56 +00:00
_VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
_AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
_TESTS = [{
2016-02-14 09:37:17 +00:00
'url': 'http://store.steampowered.com/video/105600/',
'playlist': [
2013-06-27 18:20:00 +00:00
{
2017-10-11 17:49:48 +00:00
'md5': '6a294ee0c4b1f47f5bb76a65e31e3592',
2016-02-14 09:37:17 +00:00
'info_dict': {
2017-10-11 17:49:48 +00:00
'id': '2040428',
'ext': 'mp4',
'title': 'Terraria 1.3 Trailer',
2014-04-19 17:51:04 +00:00
'playlist_index': 1,
2013-06-27 18:20:00 +00:00
}
},
{
2017-10-11 17:49:48 +00:00
'md5': '911672b20064ca3263fa89650ba5a7aa',
2016-02-14 09:37:17 +00:00
'info_dict': {
2017-10-11 17:49:48 +00:00
'id': '2029566',
'ext': 'mp4',
'title': 'Terraria 1.2 Trailer',
2014-04-19 17:51:04 +00:00
'playlist_index': 2,
2013-06-27 18:20:00 +00:00
}
}
2014-04-19 17:55:53 +00:00
],
2017-10-11 17:49:48 +00:00
'info_dict': {
'id': '105600',
'title': 'Terraria',
},
2014-04-19 17:55:53 +00:00
'params': {
'playlistend': 2,
}
}, {
'url': 'http://steamcommunity.com/sharedfiles/filedetails/?id=242472205',
'info_dict': {
2017-10-11 17:49:48 +00:00
'id': 'X8kpJBlzD2E',
'ext': 'mp4',
2017-10-11 17:49:48 +00:00
'upload_date': '20140617',
'title': 'FRONTIERS - Trapping',
'description': 'md5:bf6f7f773def614054089e5769c12a6e',
'uploader': 'AAD Productions',
'uploader_id': 'AtomicAgeDogGames',
}
}]
2013-06-27 18:20:00 +00:00
2013-06-23 20:02:56 +00:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
fileID = m.group('fileID')
if fileID:
videourl = url
playlist_id = fileID
else:
gameID = m.group('gameID')
playlist_id = gameID
videourl = self._VIDEO_PAGE_TEMPLATE % playlist_id
self._set_cookie('steampowered.com', 'mature_content', '1')
webpage = self._download_webpage(videourl, playlist_id)
2013-06-23 20:02:56 +00:00
if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
videourl = self._AGECHECK_TEMPLATE % playlist_id
2013-06-23 20:02:56 +00:00
self.report_age_confirmation()
webpage = self._download_webpage(videourl, playlist_id)
2017-10-11 17:49:48 +00:00
flash_vars = self._parse_json(self._search_regex(
r'(?s)rgMovieFlashvars\s*=\s*({.+?});', webpage,
'flash vars'), playlist_id, js_to_json)
playlist_title = None
entries = []
if fileID:
2017-10-11 17:49:48 +00:00
playlist_title = get_element_by_class('workshopItemTitle', webpage)
for movie in flash_vars.values():
if not movie:
continue
youtube_id = movie.get('YOUTUBE_VIDEO_ID')
if not youtube_id:
continue
entries.append({
'_type': 'url',
'url': youtube_id,
'ie_key': 'Youtube',
})
else:
2017-10-11 17:49:48 +00:00
playlist_title = get_element_by_class('apphub_AppName', webpage)
for movie_id, movie in flash_vars.items():
if not movie:
continue
video_id = self._search_regex(r'movie_(\d+)', movie_id, 'video id', fatal=False)
title = movie.get('MOVIE_NAME')
if not title or not video_id:
continue
entry = {
'id': video_id,
2017-10-11 17:49:48 +00:00
'title': title.replace('+', ' '),
}
formats = []
flv_url = movie.get('FILENAME')
if flv_url:
formats.append({
'format_id': 'flv',
'url': flv_url,
})
highlight_element = self._search_regex(
r'(<div[^>]+id="highlight_movie_%s"[^>]+>)' % video_id,
webpage, 'highlight element', fatal=False)
if highlight_element:
highlight_attribs = extract_attributes(highlight_element)
if highlight_attribs:
entry['thumbnail'] = highlight_attribs.get('data-poster')
for quality in ('', '-hd'):
for ext in ('webm', 'mp4'):
video_url = highlight_attribs.get('data-%s%s-source' % (ext, quality))
if video_url:
formats.append({
'format_id': ext + quality,
'url': video_url,
})
if not formats:
continue
entry['formats'] = formats
entries.append(entry)
if not entries:
raise ExtractorError('Could not find any videos')
2013-06-23 20:02:56 +00:00
2017-10-11 17:49:48 +00:00
return self.playlist_result(entries, playlist_id, playlist_title)