R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

reverted commit 7f4b465 in favor of much easier fix: using utf-8-sig for encoding

Browse Source
This commit is contained in:
Christian Pointner 2016-09-02 01:36:46 +02:00
parent 2ac405397e
commit a72b74c6f9
3 changed files with 9 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/cba.py
View File

@ -50,7 +50,8 @@ class CBAIE(InfoExtractor):
description = ''
formats = []
posts_result = self._download_json(api_posts_url, video_id, 'query posts api-endpoint', 'unable to query posts api-endpoint')
posts_result = self._download_json(api_posts_url, video_id, 'query posts api-endpoint',
'unable to query posts api-endpoint', encoding='utf-8-sig')
try:
title = posts_result['title']['raw']
except KeyError:
@ -71,7 +72,7 @@ class CBAIE(InfoExtractor):
api_media_url = update_url_query(api_media_url, {'c': self._API_KEY})
media_result = self._download_json(api_media_url, video_id, 'query media api-endpoint%s' % api_key_str,
'unable to qeury media api-endpoint%s' % api_key_str)
'unable to qeury media api-endpoint%s' % api_key_str, encoding='utf-8-sig')
for media in media_result:
try:
url = media['source_url']

5
youtube_dl/extractor/common.py
View File

@ -57,7 +57,6 @@ from ..utils import (
parse_m3u8_attributes,
extract_attributes,
parse_codecs,
parse_strip_bom,
)
@ -439,10 +438,6 @@ class InfoExtractor(object):
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
webpage_bytes, bom_enc = parse_strip_bom(webpage_bytes)
if not encoding:
encoding = bom_enc
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
if not encoding:

20
youtube_dl/utils.py
View File

@ -2235,8 +2235,8 @@ def age_restricted(content_limit, age_limit):
return age_limit < content_limit
def parse_strip_bom(data):
""" try to find Unicode BOM and strip it. """
def is_html(first_bytes):
""" Detect whether a file contains HTML by examining its first bytes. """
BOMS = [
(b'\xef\xbb\xbf', 'utf-8'),
@ -2246,20 +2246,12 @@ def parse_strip_bom(data):
(b'\xfe\xff', 'utf-16-be'),
]
for bom, enc in BOMS:
if data.startswith(bom):
return data[len(bom):], enc
if first_bytes.startswith(bom):
s = first_bytes[len(bom):].decode(enc, 'replace')
break
else:
return data, None
s = first_bytes.decode('utf-8', 'replace')
def is_html(first_bytes):
""" Detect whether a file contains HTML by examining its first bytes. """
first_bytes, enc = parse_strip_bom(first_bytes)
if enc == None:
enc = 'utf-8'
s = first_bytes.decode(enc, 'replace')
return re.match(r'^\s*<', s)