Compare commits

...

9 Commits

Author SHA1 Message Date
Philipp Hagemeister
8829650513 release 2015.02.10.1 2015-02-10 01:46:09 +01:00
Philipp Hagemeister
c73fae1e2e [commonmistakes] Detect BOMs at the beginning of URLs
Reported at https://bugzilla.redhat.com/show_bug.cgi?id=1093517 .
2015-02-10 01:40:55 +01:00
Philipp Hagemeister
834bf069d2 [bandcamp] Correct variable name 2015-02-10 01:37:14 +01:00
Philipp Hagemeister
c06a9fa34f Use snake_case instead of camelCase 2015-02-10 01:36:38 +01:00
Philipp Hagemeister
753fad4adc [commonmistakes] Correct logic error 2015-02-10 01:34:01 +01:00
Philipp Hagemeister
34814eb66e release 2015.02.10 2015-02-10 01:19:52 +01:00
Philipp Hagemeister
3a5bcd0326 [extractor/common] Wrap extractor errors (Fixes #1194)
For now, we just wrap some common errors. More may follow. We do not want to catch actual programming errors in the extractors, such as 1 // 0.
2015-02-10 01:17:23 +01:00
Philipp Hagemeister
99c2398bc6 [bandcamp] Use our API to get more stable error messages (#1194) 2015-02-09 19:08:51 +01:00
Philipp Hagemeister
28f1272870 [svtplay] Correct test case 2015-02-09 16:05:01 +01:00
7 changed files with 56 additions and 28 deletions

View File

@@ -74,7 +74,7 @@ from .collegehumor import CollegeHumorIE
from .collegerama import CollegeRamaIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE

View File

@@ -72,26 +72,29 @@ class BandcampIE(InfoExtractor):
download_link = m_download.group(1)
video_id = self._search_regex(
r'var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id')
download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
# We get the dictionary of the track from some javascript code
info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
all_info = self._parse_json(self._search_regex(
r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
info = all_info[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info['url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url)
m_url = re.match(
r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
initial_url)
# We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be
# in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
final_url = self._search_regex(
r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
return {
'id': video_id,

View File

@@ -264,8 +264,15 @@ class InfoExtractor(object):
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
try:
self.initialize()
return self._real_extract(url)
except ExtractorError:
raise
except compat_http_client.IncompleteRead as e:
raise ExtractorError('A network error has occured.', cause=e, expected=True)
except (KeyError,) as e:
raise ExtractorError('An extractor error has occured.', cause=e)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""

View File

@@ -24,6 +24,23 @@ class CommonMistakesIE(InfoExtractor):
'That doesn\'t make any sense. '
'Simply remove the parameter in your command or configuration.'
) % url
if self._downloader.params.get('verbose'):
if not self._downloader.params.get('verbose'):
msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
raise ExtractorError(msg, expected=True)
class UnicodeBOMIE(InfoExtractor):
IE_DESC = False
_VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
_TESTS = [{
'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
'only_matching': True,
}]
def _real_extract(self, url):
real_url = self._match_id(url)
self.report_warning(
'Your URL starts with a Byte Order Mark (BOM). '
'Removing the BOM and looking for "%s" ...' % real_url)
return self.url_result(real_url)

View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
@@ -10,13 +11,13 @@ class SVTPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
'md5': '2521cd644e862936cf2e698206e47385',
'md5': 'f4a184968bc9c802a9b41316657aaa80',
'info_dict': {
'id': '3966754',
'id': '2609989',
'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer',
'title': 'SM veckan vinter, Örebro - Rally, final',
'duration': 4500,
'thumbnail': 're:^https?://.*\.jpg$',
'thumbnail': 're:^https?://.*[\.-]jpg$',
},
}

View File

@@ -734,22 +734,22 @@ def parseOpts(overrideArguments=None):
if opts.verbose:
write_string('[debug] Override config: ' + repr(overrideArguments) + '\n')
else:
commandLineConf = sys.argv[1:]
if '--ignore-config' in commandLineConf:
systemConf = []
userConf = []
command_line_conf = sys.argv[1:]
if '--ignore-config' in command_line_conf:
system_conf = []
user_conf = []
else:
systemConf = _readOptions('/etc/youtube-dl.conf')
if '--ignore-config' in systemConf:
userConf = []
system_conf = _readOptions('/etc/youtube-dl.conf')
if '--ignore-config' in system_conf:
user_conf = []
else:
userConf = _readUserConf()
argv = systemConf + userConf + commandLineConf
user_conf = _readUserConf()
argv = system_conf + user_conf + command_line_conf
opts, args = parser.parse_args(argv)
if opts.verbose:
write_string('[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
write_string('[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
write_string('[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
write_string('[debug] System config: ' + repr(_hide_login_info(system_conf)) + '\n')
write_string('[debug] User config: ' + repr(_hide_login_info(user_conf)) + '\n')
write_string('[debug] Command-line args: ' + repr(_hide_login_info(command_line_conf)) + '\n')
return parser, opts, args

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.02.09.3'
__version__ = '2015.02.10.1'