commit: fca6dba8b80286ae6d3ca0a60c4799c220a52650
parent e2f8bf5888274b95513b430e0f20261120699b4b
Author: Sergey M․ <dstftw@gmail.com>
Date: Sat, 29 Feb 2020 19:08:44 +0700
[YoutubeDL] Force redirect URL to unicode on python 2
Diffstat:
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
@@ -92,6 +92,7 @@ from .utils import (
YoutubeDLCookieJar,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
+ YoutubeDLRedirectHandler,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
@@ -2343,6 +2344,7 @@ class YoutubeDL(object):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
+ redirect_handler = YoutubeDLRedirectHandler()
data_handler = compat_urllib_request_DataHandler()
# When passing our own FileHandler instance, build_opener won't add the
@@ -2356,7 +2358,7 @@ class YoutubeDL(object):
file_handler.file_open = file_open
opener = compat_urllib_request.build_opener(
- proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler)
+ proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
@@ -2795,6 +2795,15 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
https_response = http_response
+class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
+ if sys.version_info[0] < 3:
+ def redirect_request(self, req, fp, code, msg, headers, newurl):
+ # On python 2 urlh.geturl() may sometimes return redirect URL
+ # as byte string instead of unicode. This workaround allows
+ # to force it always return unicode.
+ return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl))
+
+
def extract_timezone(date_str):
m = re.search(
r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',