]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/facebook.py
6 from .common
import InfoExtractor
12 compat_urllib_request
,
18 class FacebookIE(InfoExtractor
):
19 """Information Extractor for Facebook"""
21 _VALID_URL
= r
'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
22 _LOGIN_URL
= 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
23 _NETRC_MACHINE
= 'facebook'
26 u
'url': u
'https://www.facebook.com/photo.php?v=120708114770723',
27 u
'file': u
'120708114770723.mp4',
28 u
'md5': u
'48975a41ccc4b7a581abd68651c1a5a8',
31 u
"title": u
"PEOPLE ARE AWESOME 2013"
35 def report_login(self
):
36 """Report attempt to log in."""
37 self
.to_screen(u
'Logging in')
39 def _real_initialize(self
):
40 if self
._downloader
is None:
45 downloader_params
= self
._downloader
.params
47 # Attempt to use provided username and password or .netrc data
48 if downloader_params
.get('username', None) is not None:
49 useremail
= downloader_params
['username']
50 password
= downloader_params
['password']
51 elif downloader_params
.get('usenetrc', False):
53 info
= netrc
.netrc().authenticators(self
._NETRC
_MACHINE
)
58 raise netrc
.NetrcParseError('No authenticators for %s' % self
._NETRC
_MACHINE
)
59 except (IOError, netrc
.NetrcParseError
) as err
:
60 self
._downloader
.report_warning(u
'parsing .netrc: %s' % compat_str(err
))
72 request
= compat_urllib_request
.Request(self
._LOGIN
_URL
, compat_urllib_parse
.urlencode(login_form
))
75 login_results
= compat_urllib_request
.urlopen(request
).read()
76 if re
.search(r
'<form(.*)name="login"(.*)</form>', login_results
) is not None:
77 self
._downloader
.report_warning(u
'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
79 except (compat_urllib_error
.URLError
, compat_http_client
.HTTPException
, socket
.error
) as err
:
80 self
._downloader
.report_warning(u
'unable to log in: %s' % compat_str(err
))
83 def _real_extract(self
, url
):
84 mobj
= re
.match(self
._VALID
_URL
, url
)
86 raise ExtractorError(u
'Invalid URL: %s' % url
)
87 video_id
= mobj
.group('ID')
89 url
= 'https://www.facebook.com/video/video.php?v=%s' % video_id
90 webpage
= self
._download
_webpage
(url
, video_id
)
92 BEFORE
= '{swf.addParam(param[0], param[1]);});\n'
93 AFTER
= '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
94 m
= re
.search(re
.escape(BEFORE
) + '(.*?)' + re
.escape(AFTER
), webpage
)
96 raise ExtractorError(u
'Cannot parse data')
97 data
= dict(json
.loads(m
.group(1)))
98 params_raw
= compat_urllib_parse
.unquote(data
['params'])
99 params
= json
.loads(params_raw
)
100 video_data
= params
['video_data'][0]
101 video_url
= video_data
.get('hd_src')
103 video_url
= video_data
['sd_src']
105 raise ExtractorError(u
'Cannot find video URL')
106 video_duration
= int(video_data
['video_duration'])
107 thumbnail
= video_data
['thumbnail_src']
109 video_title
= self
._html
_search
_regex
('<h2 class="uiHeaderTitle">([^<]+)</h2>',
114 'title': video_title
,
117 'duration': video_duration
,
118 'thumbnail': thumbnail
,