Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

py3 compat

Browse Source
This commit is contained in:
Kovid Goyal 2020-04-29 08:51:32 +05:30
parent 92c412996f
commit 9e88dfd3b4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/calibre/ebooks/html/input.py
View File

@ -91,6 +91,7 @@ class HTMLFile(object):
''' '''
HTML_PAT = re.compile(r'<\s*html', re.IGNORECASE) HTML_PAT = re.compile(r'<\s*html', re.IGNORECASE)
HTML_PAT_BIN = re.compile(br'<\s*html', re.IGNORECASE)
TITLE_PAT = re.compile('<title>([^<>]+)</title>', re.IGNORECASE) TITLE_PAT = re.compile('<title>([^<>]+)</title>', re.IGNORECASE)
LINK_PAT = re.compile( LINK_PAT = re.compile(
r'<\s*a\s+.*?href\s*=\s*(?:(?:"(?P<url1>[^"]+)")|(?:\'(?P<url2>[^\']+)\')|(?P<url3>[^\s>]+))', r'<\s*a\s+.*?href\s*=\s*(?:(?:"(?P<url1>[^"]+)")|(?:\'(?P<url2>[^\']+)\')|(?P<url3>[^\s>]+))',
@ -115,10 +116,13 @@ class HTMLFile(object):
encoding = detect_xml_encoding(src)[1] encoding = detect_xml_encoding(src)[1]
if encoding: if encoding:
try: try:
header = header.decode(encoding, errors='ignore') header = header.decode(encoding, errors='replace')
except ValueError: except ValueError:
pass pass
self.is_binary = level > 0 and not bool(self.HTML_PAT.search(header)) self.is_binary = False
if level > 0:
pat = self.HTML_PAT_BIN if isinstance(header, bytes) else self.HTML_PAT
self.is_binary = not bool(pat.search(header))
if not self.is_binary: if not self.is_binary:
src += f.read() src += f.read()
except IOError as err: except IOError as err: