projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
lazy extractors: specify the encoding
[youtube-dl]
/
youtube_dl
/
YoutubeDL.py
diff --git
a/youtube_dl/YoutubeDL.py
b/youtube_dl/YoutubeDL.py
index 8c651cd52375e1dcf986307b57f447fce4025543..f18a8e840553528703e79cf3dd2415173a568d0e 100755
(executable)
--- a/
youtube_dl/YoutubeDL.py
+++ b/
youtube_dl/YoutubeDL.py
@@
-39,6
+39,8
@@
from .compat import (
compat_urllib_request_DataHandler,
)
from .utils import (
compat_urllib_request_DataHandler,
)
from .utils import (
+ age_restricted,
+ args_to_str,
ContentTooShortError,
date_from_str,
DateRange,
ContentTooShortError,
date_from_str,
DateRange,
@@
-58,13
+60,16
@@
from .utils import (
PagedList,
parse_filesize,
PerRequestProxyHandler,
PagedList,
parse_filesize,
PerRequestProxyHandler,
- PostProcessingError,
platform_name,
platform_name,
+ PostProcessingError,
preferredencoding,
preferredencoding,
+ prepend_extension,
render_table,
render_table,
+ replace_extension,
SameFileError,
sanitize_filename,
sanitize_path,
SameFileError,
sanitize_filename,
sanitize_path,
+ sanitize_url,
sanitized_Request,
std_headers,
subtitles_filename,
sanitized_Request,
std_headers,
subtitles_filename,
@@
-75,13
+80,9
@@
from .utils import (
write_string,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
write_string,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
- prepend_extension,
- replace_extension,
- args_to_str,
- age_restricted,
)
from .cache import Cache
)
from .cache import Cache
-from .extractor import get_info_extractor, gen_extractors
+from .extractor import get_info_extractor, gen_extractor
_classe
s
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
@@
-377,8
+378,9
@@
class YoutubeDL(object):
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
- self._ies_instances[ie.ie_key()] = ie
- ie.set_downloader(self)
+ if not isinstance(ie, type):
+ self._ies_instances[ie.ie_key()] = ie
+ ie.set_downloader(self)
def get_info_extractor(self, ie_key):
"""
def get_info_extractor(self, ie_key):
"""
@@
-396,7
+398,7
@@
class YoutubeDL(object):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
"""
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
"""
- for ie in gen_extractors():
+ for ie in gen_extractor
_classe
s():
self.add_info_extractor(ie)
def add_post_processor(self, pp):
self.add_info_extractor(ie)
def add_post_processor(self, pp):
@@
-660,6
+662,7
@@
class YoutubeDL(object):
if not ie.suitable(url):
continue
if not ie.suitable(url):
continue
+ ie = self.get_info_extractor(ie.ie_key())
if not ie.working():
self.report_warning('The program functionality for this site has been marked as broken, '
'and will probably not work.')
if not ie.working():
self.report_warning('The program functionality for this site has been marked as broken, '
'and will probably not work.')
@@
-905,7
+908,7
@@
class YoutubeDL(object):
'*=': lambda attr, value: value in attr,
}
str_operator_rex = re.compile(r'''(?x)
'*=': lambda attr, value: value in attr,
}
str_operator_rex = re.compile(r'''(?x)
- \s*(?P<key>ext|acodec|vcodec|container|protocol)
+ \s*(?P<key>ext|acodec|vcodec|container|protocol
|format_id
)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
\s*(?P<value>[a-zA-Z0-9._-]+)
\s*$
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
\s*(?P<value>[a-zA-Z0-9._-]+)
\s*$
@@
-1229,6
+1232,7
@@
class YoutubeDL(object):
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
for i, t in enumerate(thumbnails):
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
for i, t in enumerate(thumbnails):
+ t['url'] = sanitize_url(t['url'])
if t.get('width') and t.get('height'):
t['resolution'] = '%dx%d' % (t['width'], t['height'])
if t.get('id') is None:
if t.get('width') and t.get('height'):
t['resolution'] = '%dx%d' % (t['width'], t['height'])
if t.get('id') is None:
@@
-1238,7
+1242,10
@@
class YoutubeDL(object):
self.list_thumbnails(info_dict)
return
self.list_thumbnails(info_dict)
return
- if thumbnails and 'thumbnail' not in info_dict:
+ thumbnail = info_dict.get('thumbnail')
+ if thumbnail:
+ info_dict['thumbnail'] = sanitize_url(thumbnail)
+ elif thumbnails:
info_dict['thumbnail'] = thumbnails[-1]['url']
if 'display_id' not in info_dict and 'id' in info_dict:
info_dict['thumbnail'] = thumbnails[-1]['url']
if 'display_id' not in info_dict and 'id' in info_dict:
@@
-1263,6
+1270,8
@@
class YoutubeDL(object):
if subtitles:
for _, subtitle in subtitles.items():
for subtitle_format in subtitle:
if subtitles:
for _, subtitle in subtitles.items():
for subtitle_format in subtitle:
+ if subtitle_format.get('url'):
+ subtitle_format['url'] = sanitize_url(subtitle_format['url'])
if 'ext' not in subtitle_format:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
if 'ext' not in subtitle_format:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
@@
-1292,6
+1301,8
@@
class YoutubeDL(object):
if 'url' not in format:
raise ExtractorError('Missing "url" key in result (index %d)' % i)
if 'url' not in format:
raise ExtractorError('Missing "url" key in result (index %d)' % i)
+ format['url'] = sanitize_url(format['url'])
+
if format.get('format_id') is None:
format['format_id'] = compat_str(i)
else:
if format.get('format_id') is None:
format['format_id'] = compat_str(i)
else:
@@
-1836,7
+1847,7
@@
class YoutubeDL(object):
if fdict.get('language'):
if res:
res += ' '
if fdict.get('language'):
if res:
res += ' '
- res += '[%s]' % fdict['language']
+ res += '[%s]
' % fdict['language']
if fdict.get('format_note') is not None:
res += fdict['format_note'] + ' '
if fdict.get('tbr') is not None:
if fdict.get('format_note') is not None:
res += fdict['format_note'] + ' '
if fdict.get('tbr') is not None: