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

Fix #1140 (text has random underlining)

Browse Source
This commit is contained in:
Kovid Goyal 2008-10-07 18:22:01 -07:00
parent 2b0cf3fed5
commit c769c35b1d
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/html.py
View File

@ -436,11 +436,13 @@ class Parser(PreProcessor, LoggingInterface):
''' Create lxml ElementTree from HTML ''' ''' Create lxml ElementTree from HTML '''
self.log_info('\tParsing '+os.sep.join(self.htmlfile.path.split(os.sep)[-3:])) self.log_info('\tParsing '+os.sep.join(self.htmlfile.path.split(os.sep)[-3:]))
src = open(self.htmlfile.path, 'rb').read().decode(self.htmlfile.encoding, 'replace').strip() src = open(self.htmlfile.path, 'rb').read().decode(self.htmlfile.encoding, 'replace').strip()
src = src[src.find('<'):]
src = self.preprocess(src) src = self.preprocess(src)
# lxml chokes on unicode input when it contains encoding declarations # lxml chokes on unicode input when it contains encoding declarations
for pat in ENCODING_PATS: for pat in ENCODING_PATS:
src = pat.sub('', src) src = pat.sub('', src)
src = src[src.find('<'):]
# Remove unclosed <style> tag as that messes up lxml's parsing
src = re.sub(r'<style>\s*</head>', '', src)
try: try:
self.root = fromstring(src) self.root = fromstring(src)
except: except: