Mirror
/
youtube-dl
mirror of https://github.com/ytdl-org/youtube-dl.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[facebook] Modernize

pull/2516/merge
Philipp Hagemeister 2014-03-04 03:36:54 +01:00
parent e2cc7983e9
commit cb3bb2cfef
1 changed files with 23 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
youtube_dl/extractor/facebook.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import json import json
import re import re
import socket import socket
@ -26,12 +28,13 @@ class FacebookIE(InfoExtractor):
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1' _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1' _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
_NETRC_MACHINE = 'facebook' _NETRC_MACHINE = 'facebook'
IE_NAME = u'facebook' IE_NAME = 'facebook'
_TEST = { _TEST = {
u'url': u'https://www.facebook.com/photo.php?v=120708114770723', 'url': 'https://www.facebook.com/photo.php?v=120708114770723',
u'file': u'120708114770723.mp4', 'md5': '48975a41ccc4b7a581abd68651c1a5a8',
u'md5': u'48975a41ccc4b7a581abd68651c1a5a8', 'info_dict': {
u'info_dict': { 'id': '120708114770723',
'ext': 'mp4',
u"duration": 279, u"duration": 279,
u"title": u"PEOPLE ARE AWESOME 2013" u"title": u"PEOPLE ARE AWESOME 2013"
} }
@ -39,7 +42,7 @@ class FacebookIE(InfoExtractor):
def report_login(self): def report_login(self):
"""Report attempt to log in.""" """Report attempt to log in."""
self.to_screen(u'Logging in') self.to_screen('Logging in')
def _login(self): def _login(self):
(useremail, password) = self._get_login_info() (useremail, password) = self._get_login_info()
@ -50,9 +53,9 @@ class FacebookIE(InfoExtractor):
login_page_req.add_header('Cookie', 'locale=en_US') login_page_req.add_header('Cookie', 'locale=en_US')
self.report_login() self.report_login()
login_page = self._download_webpage(login_page_req, None, note=False, login_page = self._download_webpage(login_page_req, None, note=False,
errnote=u'Unable to download login page') errnote='Unable to download login page')
lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd') lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, 'lsd')
lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd') lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
login_form = { login_form = {
'email': useremail, 'email': useremail,
@ -70,22 +73,22 @@ class FacebookIE(InfoExtractor):
try: try:
login_results = compat_urllib_request.urlopen(request).read() login_results = compat_urllib_request.urlopen(request).read()
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return return
check_form = { check_form = {
'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'), 'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, 'fb_dtsg'),
'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'), 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, 'nh'),
'name_action_selected': 'dont_save', 'name_action_selected': 'dont_save',
'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, u'continue'), 'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, 'continue'),
} }
check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, compat_urllib_parse.urlencode(check_form)) check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, compat_urllib_parse.urlencode(check_form))
check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
check_response = compat_urllib_request.urlopen(check_req).read() check_response = compat_urllib_request.urlopen(check_req).read()
if re.search(r'id="checkpointSubmitButton"', check_response) is not None: if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
self._downloader.report_warning(u'Unable to confirm login, you have to login in your brower and authorize the login.') self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) self._downloader.report_warning('unable to log in: %s' % compat_str(err))
return return
def _real_initialize(self): def _real_initialize(self):
@ -94,7 +97,7 @@ class FacebookIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError('Invalid URL: %s' % url)
video_id = mobj.group('id') video_id = mobj.group('id')
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
@ -107,10 +110,10 @@ class FacebookIE(InfoExtractor):
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None: if m_msg is not None:
raise ExtractorError( raise ExtractorError(
u'The video is not available, Facebook said: "%s"' % m_msg.group(1), 'The video is not available, Facebook said: "%s"' % m_msg.group(1),
expected=True) expected=True)
else: else:
raise ExtractorError(u'Cannot parse data') raise ExtractorError('Cannot parse data')
data = dict(json.loads(m.group(1))) data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse.unquote(data['params']) params_raw = compat_urllib_parse.unquote(data['params'])
params = json.loads(params_raw) params = json.loads(params_raw)
@ -119,12 +122,12 @@ class FacebookIE(InfoExtractor):
if not video_url: if not video_url:
video_url = video_data['sd_src'] video_url = video_data['sd_src']
if not video_url: if not video_url:
raise ExtractorError(u'Cannot find video URL') raise ExtractorError('Cannot find video URL')
video_duration = int(video_data['video_duration']) video_duration = int(video_data['video_duration'])
thumbnail = video_data['thumbnail_src'] thumbnail = video_data['thumbnail_src']
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, u'title') r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
info = { info = {
'id': video_id, 'id': video_id,