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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
import re
import socket
from .common import InfoExtractor
from ..utils import (
compat_http_client,
compat_parse_qs,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
compat_str,
determine_ext,
ExtractorError,
)
class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com."""
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = u'metacafe'
_TESTS = [{
u"add_ie": ["Youtube"],
u"url": u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
u"file": u"_aUehQsCQtM.flv",
u"info_dict": {
u"upload_date": u"20090102",
u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
u"uploader": u"PBS",
u"uploader_id": u"PBS"
}
},
{
u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
u"file": u"an-dVVXnuY7Jh77J.mp4",
u"info_dict": {
u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
u"uploader": u"AnyClip",
}
}]
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self.to_screen(u'Retrieving disclaimer')
def _real_initialize(self):
# Retrieve disclaimer
request = compat_urllib_request.Request(self._DISCLAIMER)
try:
self.report_disclaimer()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
# Confirm age
disclaimer_form = {
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
try:
self.report_age_confirmation()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
# Retrieve video webpage to extract further information
req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
req.headers['Cookie'] = 'flashVersion=0;'
webpage = self._download_webpage(req, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
if mobj is not None:
mediaURL = compat_urllib_parse.unquote(mobj.group(1))
video_ext = mediaURL[-3:]
# Extract gdaKey if available
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
video_url = mediaURL
else:
gdaKey = mobj.group(1)
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
else:
mobj = re.search(r'<video src="([^"]+)"', webpage)
if mobj:
video_url = mobj.group(1)
video_ext = 'mp4'
else:
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
vardict = compat_parse_qs(mobj.group(1))
if 'mediaData' not in vardict:
raise ExtractorError(u'Unable to extract media URL')
mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
mediaURL = mobj.group('mediaURL').replace('\\/', '/')
video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
video_ext = determine_ext(video_url)
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
video_uploader = self._html_search_regex(r'submitter=(.*?);|<p class="By">\s*By\s*<a[^>]*>(.*?)</a>', webpage, u'uploader nickname', fatal=False)
return [{
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'ext': video_ext,
}]
|
