1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unescapeHTML,
)
class SteamIE(InfoExtractor):
_VALID_URL = r"""http://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
"""
_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'
_TEST = {
"url": "http://store.steampowered.com/video/105600/",
"playlist": [
{
"md5": "f870007cee7065d7c76b88f0a45ecc07",
"info_dict": {
'id': '81300',
'ext': 'flv',
"title": "Terraria 1.1 Trailer",
'playlist_index': 1,
}
},
{
"md5": "61aaf31a5c5c3041afb58fb83cbb5751",
"info_dict": {
'id': '80859',
'ext': 'flv',
"title": "Terraria Trailer",
'playlist_index': 2,
}
}
]
}
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE)
gameID = m.group('gameID')
videourl = self._VIDEO_PAGE_TEMPLATE % gameID
webpage = self._download_webpage(videourl, gameID)
if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
videourl = self._AGECHECK_TEMPLATE % gameID
self.report_age_confirmation()
webpage = self._download_webpage(videourl, gameID)
self.report_extraction(gameID)
game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
webpage, 'game title')
urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
mweb = re.finditer(urlRE, webpage)
namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
titles = re.finditer(namesRE, webpage)
thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
thumbs = re.finditer(thumbsRE, webpage)
videos = []
for vid,vtitle,thumb in zip(mweb,titles,thumbs):
video_id = vid.group('videoID')
title = vtitle.group('videoName')
video_url = vid.group('videoURL')
video_thumb = thumb.group('thumbnail')
if not video_url:
raise ExtractorError('Cannot find video url for %s' % video_id)
info = {
'id':video_id,
'url':video_url,
'ext': 'flv',
'title': unescapeHTML(title),
'thumbnail': video_thumb
}
videos.append(info)
return self.playlist_result(videos, gameID, game_title)
|
