aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/common.py6
-rw-r--r--youtube_dl/extractor/gorillavid.py7
-rw-r--r--youtube_dl/extractor/hostingbulk.py6
-rw-r--r--youtube_dl/extractor/played.py4
-rw-r--r--youtube_dl/extractor/primesharetv.py7
-rw-r--r--youtube_dl/extractor/promptfile.py5
-rw-r--r--youtube_dl/extractor/shared.py3
-rw-r--r--youtube_dl/extractor/twitch.py36
-rw-r--r--youtube_dl/extractor/vimeo.py6
-rw-r--r--youtube_dl/extractor/vk.py4
-rw-r--r--youtube_dl/extractor/vodlocker.py7
11 files changed, 31 insertions, 60 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index d859aea52..82f5de2d8 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -705,6 +705,12 @@ class InfoExtractor(object):
return self._html_search_meta('twitter:player', html,
'twitter card player')
+ @staticmethod
+ def _form_hidden_inputs(html):
+ return dict(re.findall(
+ r'<input\s+type="hidden"\s+name="([^"]+)"\s+(?:id="[^"]+"\s+)?value="([^"]*)"',
+ html))
+
def _sort_formats(self, formats, field_preference=None):
if not formats:
raise ExtractorError('No video formats found')
diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index 6147596e4..aabf07a20 100644
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -78,12 +78,7 @@ class GorillaVidIE(InfoExtractor):
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_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 704d0285d..63f579592 100644
--- a/youtube_dl/extractor/hostingbulk.py
+++ b/youtube_dl/extractor/hostingbulk.py
@@ -58,11 +58,7 @@ class HostingBulkIE(InfoExtractor):
r'<img src="([^"]+)".+?class="pic"',
webpage, 'thumbnail', fatal=False)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
request = compat_urllib_request.Request(url, urlencode_postdata(fields))
request.add_header('Content-type', 'application/x-www-form-urlencoded')
diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py
index 45716c75d..9fe1524f2 100644
--- a/youtube_dl/extractor/played.py
+++ b/youtube_dl/extractor/played.py
@@ -38,9 +38,7 @@ class PlayedIE(InfoExtractor):
if m_error:
raise ExtractorError(m_error.group('msg'), expected=True)
- fields = re.findall(
- r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
- data = dict(fields)
+ data = self._form_hidden_inputs(orig_webpage)
self._sleep(2, video_id)
diff --git a/youtube_dl/extractor/primesharetv.py b/youtube_dl/extractor/primesharetv.py
index 01cc3d9ea..94c9fb2cb 100644
--- a/youtube_dl/extractor/primesharetv.py
+++ b/youtube_dl/extractor/primesharetv.py
@@ -31,12 +31,7 @@ class PrimeShareTVIE(InfoExtractor):
if '>File not exist<' in webpage:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
headers = {
'Referer': url,
diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py
index f536e6e6c..81a63c7fc 100644
--- a/youtube_dl/extractor/promptfile.py
+++ b/youtube_dl/extractor/promptfile.py
@@ -35,10 +35,7 @@ class PromptFileIE(InfoExtractor):
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
- fields = dict(re.findall(r'''(?x)type="hidden"\s+
- name="(.+?)"\s+
- value="(.*?)"
- ''', webpage))
+ fields = self._form_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 9f3e944e7..7fb68bc2d 100644
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -35,8 +35,7 @@ class SharedIE(InfoExtractor):
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
- download_form = dict(re.findall(
- r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+ download_form = self._form_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 b56ee2959..af2b798fb 100644
--- a/youtube_dl/extractor/twitch.py
+++ b/youtube_dl/extractor/twitch.py
@@ -22,8 +22,8 @@ class TwitchBaseIE(InfoExtractor):
_API_BASE = 'https://api.twitch.tv'
_USHER_BASE = 'http://usher.twitch.tv'
- _LOGIN_URL = 'https://secure.twitch.tv/user/login'
- _LOGIN_POST_URL = 'https://secure-login.twitch.tv/login'
+ _LOGIN_URL = 'https://secure.twitch.tv/login'
+ _LOGIN_POST_URL = 'https://passport.twitch.tv/authorize'
_NETRC_MACHINE = 'twitch'
def _handle_error(self, response):
@@ -59,20 +59,12 @@ class TwitchBaseIE(InfoExtractor):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
- authenticity_token = self._search_regex(
- r'<input name="authenticity_token" type="hidden" value="([^"]+)"',
- login_page, 'authenticity token')
-
- login_form = {
- 'utf8': '✓'.encode('utf-8'),
- 'authenticity_token': authenticity_token,
- 'redirect_on_login': '',
- 'embed_form': 'false',
- 'mp_source_action': 'login-button',
- 'follow': '',
- 'login': username,
- 'password': password,
- }
+ login_form = self._form_hidden_inputs(login_page)
+
+ login_form.update({
+ 'login': username.encode('utf-8'),
+ 'password': password.encode('utf-8'),
+ })
request = compat_urllib_request.Request(
self._LOGIN_POST_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
@@ -80,11 +72,15 @@ class TwitchBaseIE(InfoExtractor):
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
- m = re.search(
- r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response)
- if m:
+ error_message = self._search_regex(
+ r'<div[^>]+class="subwindow_notice"[^>]*>([^<]+)</div>',
+ response, 'error message', default=None)
+ if error_message:
raise ExtractorError(
- 'Unable to login: %s' % m.group('msg').strip(), expected=True)
+ 'Unable to login. Twitch said: %s' % error_message, expected=True)
+
+ if '>Reset your password<' in response:
+ self.report_warning('Twitch asks you to reset your password, go to https://secure.twitch.tv/reset/submit')
def _prefer_source(self, formats):
try:
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index cae90205d..d63c03183 100644
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -452,11 +452,7 @@ class VimeoChannelIE(InfoExtractor):
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 = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- value="([^"]*)"
- ''', login_form))
+ fields = self._form_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 23d153031..c0292095b 100644
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -154,9 +154,7 @@ class VKIE(InfoExtractor):
login_page = self._download_webpage(
'https://vk.com', None, 'Downloading login page')
- login_form = dict(re.findall(
- r'<input\s+type="hidden"\s+name="([^"]+)"\s+(?:id="[^"]+"\s+)?value="([^"]*)"',
- login_page))
+ login_form = self._form_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 1c0966a79..431f4e2e3 100644
--- a/youtube_dl/extractor/vodlocker.py
+++ b/youtube_dl/extractor/vodlocker.py
@@ -28,12 +28,7 @@ class VodlockerIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
if fields['op'] == 'download1':
self._sleep(3, video_id) # they do detect when requests happen too fast!
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-04 05:06:26 +0000