]>
Commit | Line | Data |
---|---|---|
38cbc40a PH |
1 | import re |
2 | import socket | |
3 | ||
4 | from .common import InfoExtractor | |
5 | from ..utils import ( | |
6 | compat_http_client, | |
7 | compat_parse_qs, | |
8 | compat_urllib_error, | |
9 | compat_urllib_parse, | |
10 | compat_urllib_request, | |
11 | compat_str, | |
896d5b63 | 12 | determine_ext, |
38cbc40a PH |
13 | ExtractorError, |
14 | ) | |
15 | ||
16 | class MetacafeIE(InfoExtractor): | |
17 | """Information Extractor for metacafe.com.""" | |
18 | ||
19 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
20 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
21 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
22 | IE_NAME = u'metacafe' | |
896d5b63 | 23 | _TESTS = [{ |
83f6f68e PH |
24 | u"add_ie": ["Youtube"], |
25 | u"url": u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/", | |
26 | u"file": u"_aUehQsCQtM.flv", | |
27 | u"info_dict": { | |
28 | u"upload_date": u"20090102", | |
29 | u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!", | |
30 | u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8", | |
31 | u"uploader": u"PBS", | |
32 | u"uploader_id": u"PBS" | |
33 | } | |
896d5b63 PH |
34 | }, |
35 | { | |
36 | u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/", | |
37 | u"file": u"an-dVVXnuY7Jh77J.mp4", | |
38 | u"info_dict": { | |
39 | u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3", | |
40 | u"uploader": u"AnyClip", | |
41 | } | |
42 | }] | |
83f6f68e | 43 | |
38cbc40a PH |
44 | |
45 | def report_disclaimer(self): | |
46 | """Report disclaimer retrieval.""" | |
47 | self.to_screen(u'Retrieving disclaimer') | |
48 | ||
49 | def _real_initialize(self): | |
50 | # Retrieve disclaimer | |
51 | request = compat_urllib_request.Request(self._DISCLAIMER) | |
52 | try: | |
53 | self.report_disclaimer() | |
54 | compat_urllib_request.urlopen(request).read() | |
55 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
56 | raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) | |
57 | ||
58 | # Confirm age | |
59 | disclaimer_form = { | |
60 | 'filters': '0', | |
61 | 'submit': "Continue - I'm over 18", | |
62 | } | |
63 | request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) | |
64 | try: | |
65 | self.report_age_confirmation() | |
66 | compat_urllib_request.urlopen(request).read() | |
67 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
68 | raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) | |
69 | ||
70 | def _real_extract(self, url): | |
71 | # Extract id and simplified title from URL | |
72 | mobj = re.match(self._VALID_URL, url) | |
73 | if mobj is None: | |
74 | raise ExtractorError(u'Invalid URL: %s' % url) | |
75 | ||
76 | video_id = mobj.group(1) | |
77 | ||
78 | # Check if video comes from YouTube | |
79 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
80 | if mobj2 is not None: | |
81 | return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] | |
82 | ||
83 | # Retrieve video webpage to extract further information | |
896d5b63 PH |
84 | req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) |
85 | req.headers['Cookie'] = 'flashVersion=0;' | |
86 | webpage = self._download_webpage(req, video_id) | |
38cbc40a PH |
87 | |
88 | # Extract URL, uploader and title from webpage | |
89 | self.report_extraction(video_id) | |
90 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
91 | if mobj is not None: | |
92 | mediaURL = compat_urllib_parse.unquote(mobj.group(1)) | |
896d5b63 | 93 | video_ext = mediaURL[-3:] |
38cbc40a PH |
94 | |
95 | # Extract gdaKey if available | |
96 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
97 | if mobj is None: | |
98 | video_url = mediaURL | |
99 | else: | |
100 | gdaKey = mobj.group(1) | |
101 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
102 | else: | |
896d5b63 PH |
103 | mobj = re.search(r'<video src="([^"]+)"', webpage) |
104 | if mobj: | |
105 | video_url = mobj.group(1) | |
106 | video_ext = 'mp4' | |
107 | else: | |
108 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
109 | if mobj is None: | |
110 | raise ExtractorError(u'Unable to extract media URL') | |
111 | vardict = compat_parse_qs(mobj.group(1)) | |
112 | if 'mediaData' not in vardict: | |
113 | raise ExtractorError(u'Unable to extract media URL') | |
114 | mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0]) | |
115 | if mobj is None: | |
116 | raise ExtractorError(u'Unable to extract media URL') | |
117 | mediaURL = mobj.group('mediaURL').replace('\\/', '/') | |
118 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) | |
119 | video_ext = determine_ext(video_url) | |
38cbc40a | 120 | |
ec00e1d8 | 121 | video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title') |
896d5b63 | 122 | video_uploader = self._html_search_regex(r'submitter=(.*?);|<p class="By">\s*By\s*<a[^>]*>(.*?)</a>', webpage, u'uploader nickname', fatal=False) |
38cbc40a PH |
123 | |
124 | return [{ | |
896d5b63 PH |
125 | 'id': video_id, |
126 | 'url': video_url, | |
127 | 'uploader': video_uploader, | |
38cbc40a PH |
128 | 'upload_date': None, |
129 | 'title': video_title, | |
896d5b63 | 130 | 'ext': video_ext, |
38cbc40a | 131 | }] |