diff options
| -rw-r--r-- | youtube_dl/extractor/facebook.py | 71 | ||||
| -rw-r--r-- | youtube_dl/extractor/faz.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 20 | ||||
| -rw-r--r-- | youtube_dl/extractor/rtlnow.py | 11 | ||||
| -rw-r--r-- | youtube_dl/extractor/xhamster.py | 52 |
5 files changed, 104 insertions, 56 deletions
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 9d1bc0751..f8bdfc2d3 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -19,7 +19,8 @@ class FacebookIE(InfoExtractor): """Information Extractor for Facebook""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' - _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' + _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' _NETRC_MACHINE = 'facebook' IE_NAME = u'facebook' _TEST = { @@ -36,50 +37,56 @@ class FacebookIE(InfoExtractor): """Report attempt to log in.""" self.to_screen(u'Logging in') - def _real_initialize(self): - if self._downloader is None: - return - - useremail = None - password = None - downloader_params = self._downloader.params - - # Attempt to use provided username and password or .netrc data - if downloader_params.get('username', None) is not None: - useremail = downloader_params['username'] - password = downloader_params['password'] - elif downloader_params.get('usenetrc', False): - try: - info = netrc.netrc().authenticators(self._NETRC_MACHINE) - if info is not None: - useremail = info[0] - password = info[2] - else: - raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) - except (IOError, netrc.NetrcParseError) as err: - self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err)) - return - + def _login(self): + (useremail, password) = self._get_login_info() if useremail is None: return - # Log in + login_page_req = compat_urllib_request.Request(self._LOGIN_URL) + login_page_req.add_header('Cookie', 'locale=en_US') + self.report_login() + login_page = self._download_webpage(login_page_req, None, note=False, + errnote=u'Unable to download login page') + lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd') + lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd') + login_form = { 'email': useremail, 'pass': password, - 'login': 'Log+In' + 'lsd': lsd, + 'lgnrnd': lgnrnd, + 'next': 'http://facebook.com/home.php', + 'default_persistent': '0', + 'legacy_return': '1', + 'timezone': '-60', + 'trynum': '1', } request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') try: - self.report_login() login_results = compat_urllib_request.urlopen(request).read() 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.') return + + check_form = { + 'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'), + 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'), + 'name_action_selected': 'dont_save', + 'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, u'continue'), + } + 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_response = compat_urllib_request.urlopen(check_req).read() + 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.') 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)) return + def _real_initialize(self): + self._login() + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -93,7 +100,13 @@ class FacebookIE(InfoExtractor): AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) if not m: - raise ExtractorError(u'Cannot parse data') + m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) + if m_msg is not None: + raise ExtractorError( + u'The video is not available, Facebook said: "%s"' % m_msg.group(1), + expected=True) + else: + raise ExtractorError(u'Cannot parse data') data = dict(json.loads(m.group(1))) params_raw = compat_urllib_parse.unquote(data['params']) params = json.loads(params_raw) diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index deaa4ed2d..89ed08db4 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -5,8 +5,6 @@ import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( determine_ext, - clean_html, - get_element_by_attribute, ) @@ -47,12 +45,12 @@ class FazIE(InfoExtractor): 'format_id': code.lower(), }) - descr_html = get_element_by_attribute('class', 'Content Copy', webpage) + descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description') info = { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': clean_html(descr_html), + 'description': descr, 'thumbnail': config.find('STILL/STILL_BIG').text, } # TODO: Remove when #980 has been merged diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 69e0a7bd2..2c8fcf5ae 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -25,7 +25,7 @@ class GenericIE(InfoExtractor): { u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', u'file': u'13601338388002.mp4', - u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89', + u'md5': u'6e15c93721d7ec9e9ca3fdbf07982cfd', u'info_dict': { u"uploader": u"www.hodiho.fr", u"title": u"R\u00e9gis plante sa Jeep" @@ -41,7 +41,17 @@ class GenericIE(InfoExtractor): u"uploader_id": u"skillsmatter", u"uploader": u"Skills Matter", } - } + }, + # bandcamp page with custom domain + { + u'url': u'http://bronyrock.com/track/the-pony-mash', + u'file': u'3235767654.mp3', + u'info_dict': { + u'title': u'The Pony Mash', + u'uploader': u'M_Pallante', + }, + u'skip': u'There is a limit of 200 free downloads / month for the test song', + }, ] def report_download_webpage(self, video_id): @@ -155,6 +165,12 @@ class GenericIE(InfoExtractor): surl = unescapeHTML(mobj.group(1)) return self.url_result(surl, 'Youtube') + # Look for Bandcamp pages with custom domain + mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) + if mobj is not None: + burl = unescapeHTML(mobj.group(1)) + return self.url_result(burl, 'Bandcamp') + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index d1b08c9bc..9ac7c3be8 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -63,13 +63,12 @@ class RTLnowIE(InfoExtractor): }, }, { - u'url': u'http://www.rtlnitronow.de/recht-ordnung/lebensmittelkontrolle-erlangenordnungsamt-berlin.php?film_id=127367&player=1&season=1', - u'file': u'127367.flv', + u'url': u'http://www.rtlnitronow.de/recht-ordnung/stadtpolizei-frankfurt-gerichtsvollzieher-leipzig.php?film_id=129679&player=1&season=1', + u'file': u'129679.flv', u'info_dict': { - u'upload_date': u'20130926', - u'title': u'Recht & Ordnung - Lebensmittelkontrolle Erlangen/Ordnungsamt...', - u'description': u'Lebensmittelkontrolle Erlangen/Ordnungsamt Berlin', - u'thumbnail': u'http://autoimg.static-fra.de/nitronow/344787/1500x1500/image2.jpg', + u'upload_date': u'20131016', + u'title': u'Recht & Ordnung - Stadtpolizei Frankfurt/ Gerichtsvollzieher...', + u'description': u'Stadtpolizei Frankfurt/ Gerichtsvollzieher Leipzig', }, u'params': { u'skip_download': True, diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 81c4be326..7444d3393 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -36,21 +36,25 @@ class XHamsterIE(InfoExtractor): }] def _real_extract(self,url): + def extract_video_url(webpage): + mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + if len(mobj.group('server')) == 0: + return compat_urllib_parse.unquote(mobj.group('file')) + else: + return mobj.group('server')+'/key='+mobj.group('file') + + def is_hd(webpage): + return webpage.find('<div class=\'icon iconHD\'>') != -1 + mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') seo = mobj.group('seo') - mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo) + mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo) webpage = self._download_webpage(mrss_url, video_id) - mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - if len(mobj.group('server')) == 0: - video_url = compat_urllib_parse.unquote(mobj.group('file')) - else: - video_url = mobj.group('server')+'/key='+mobj.group('file') - video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, u'title') @@ -76,14 +80,32 @@ class XHamsterIE(InfoExtractor): age_limit = self._rta_search(webpage) - return [{ - 'id': video_id, - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': video_title, + video_url = extract_video_url(webpage) + hd = is_hd(webpage) + formats = [{ + 'url': video_url, + 'ext': determine_ext(video_url), + 'format': 'hd' if hd else 'sd', + 'format_id': 'hd' if hd else 'sd', + }] + if not hd: + webpage = self._download_webpage(mrss_url+'?hd', video_id) + if is_hd(webpage): + video_url = extract_video_url(webpage) + formats.append({ + 'url': video_url, + 'ext': determine_ext(video_url), + 'format': 'hd', + 'format_id': 'hd', + }) + + return { + 'id': video_id, + 'title': video_title, + 'formats': formats, 'description': video_description, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'thumbnail': video_thumbnail, 'age_limit': age_limit, - }] + } |