From f8da79f828637757889f3f35d7adfa9aabbfc721 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 14 Jul 2015 22:36:30 +0600 Subject: [PATCH] [extractor/common] Improve _form_hidden_inputs and rename to _hidden_inputs --- youtube_dl/extractor/common.py | 15 +++++++++++---- youtube_dl/extractor/gorillavid.py | 2 +- youtube_dl/extractor/hostingbulk.py | 2 +- youtube_dl/extractor/played.py | 2 +- youtube_dl/extractor/primesharetv.py | 2 +- youtube_dl/extractor/promptfile.py | 2 +- youtube_dl/extractor/shared.py | 2 +- youtube_dl/extractor/twitch.py | 2 +- youtube_dl/extractor/vimeo.py | 2 +- youtube_dl/extractor/vk.py | 2 +- youtube_dl/extractor/vodlocker.py | 2 +- 11 files changed, 21 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 82f5de2d8..315fe4a72 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -706,10 +706,17 @@ def _twitter_search_player(self, html): 'twitter card player') @staticmethod - def _form_hidden_inputs(html): - return dict(re.findall( - r'["\'])hidden(?P=q_hidden)\s+ + name=(?P["\'])(?P.+?)(?P=q_name)\s+ + (?:id=(?P["\']).+?(?P=q_id)\s+)? + value=(?P["\'])(?P.*?)(?P=q_value) + ''', html) + ]) def _sort_formats(self, formats, field_preference=None): if not formats: diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py index aabf07a20..f006f0cb1 100644 --- a/youtube_dl/extractor/gorillavid.py +++ b/youtube_dl/extractor/gorillavid.py @@ -78,7 +78,7 @@ def _real_extract(self, url): if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) - fields = self._form_hidden_inputs(webpage) + fields = self._hidden_inputs(webpage) if fields['op'] == 'download1': countdown = int_or_none(self._search_regex( diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py index 63f579592..a3154cfde 100644 --- a/youtube_dl/extractor/hostingbulk.py +++ b/youtube_dl/extractor/hostingbulk.py @@ -58,7 +58,7 @@ def _real_extract(self, url): r'File not exist<' in webpage: raise ExtractorError('Video %s does not exist' % video_id, expected=True) - fields = self._form_hidden_inputs(webpage) + fields = self._hidden_inputs(webpage) headers = { 'Referer': url, diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index 81a63c7fc..8190ed676 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -35,7 +35,7 @@ def _real_extract(self, url): raise ExtractorError('Video %s does not exist' % video_id, expected=True) - fields = self._form_hidden_inputs(webpage) + fields = self._hidden_inputs(webpage) post = compat_urllib_parse.urlencode(fields) req = compat_urllib_request.Request(url, post) req.add_header('Content-type', 'application/x-www-form-urlencoded') diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 6e2b94e7d..a07677686 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -34,7 +34,7 @@ def _real_extract(self, url): raise ExtractorError( 'Video %s does not exist' % video_id, expected=True) - download_form = self._form_hidden_inputs(webpage) + download_form = self._hidden_inputs(webpage) request = compat_urllib_request.Request( url, compat_urllib_parse.urlencode(download_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index af2b798fb..92b6dc1b8 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -59,7 +59,7 @@ def _login(self): login_page = self._download_webpage( self._LOGIN_URL, None, 'Downloading login page') - login_form = self._form_hidden_inputs(login_page) + login_form = self._hidden_inputs(login_page) login_form.update({ 'login': username.encode('utf-8'), diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index d63c03183..10d6745af 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -452,7 +452,7 @@ def _login_list_password(self, page_url, list_id, webpage): password = self._downloader.params.get('videopassword', None) if password is None: raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) - fields = self._form_hidden_inputs(login_form) + fields = self._hidden_inputs(login_form) token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token') fields['token'] = token fields['password'] = password diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 8ac3aeac0..8f677cae3 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -168,7 +168,7 @@ def _login(self): login_page = self._download_webpage( 'https://vk.com', None, 'Downloading login page') - login_form = self._form_hidden_inputs(login_page) + login_form = self._hidden_inputs(login_page) login_form.update({ 'email': username.encode('cp1251'), diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py index 4804692bf..ccf1928b5 100644 --- a/youtube_dl/extractor/vodlocker.py +++ b/youtube_dl/extractor/vodlocker.py @@ -26,7 +26,7 @@ def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - fields = self._form_hidden_inputs(webpage) + fields = self._hidden_inputs(webpage) if fields['op'] == 'download1': self._sleep(3, video_id) # they do detect when requests happen too fast!