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 handling of '

Browse Source
This commit is contained in:
Kovid Goyal 2007-08-20 00:50:55 +00:00
parent 7679166dbe
commit d5bd948404
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -50,10 +50,10 @@ class HTMLConverter(object):
SELECTOR_PAT = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}")
PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE)
IGNORED_TAGS = (Comment, Declaration, ProcessingInstruction)
replaced_entities = [ 'amp', 'lt', 'gt' , 'ldquo', 'rdquo', 'lsquo', 'rsquo' ]
replaced_entities = [ 'amp', 'lt', 'gt' , 'ldquo', 'rdquo', 'lsquo', 'rsquo']
patterns = [ re.compile('&'+i+';') for i in replaced_entities ]
targets = [ unichr(name2codepoint[i]) for i in replaced_entities ]
ENTITY_RULES = zip(patterns, targets)
ENTITY_RULES = zip(patterns, targets) + [(re.compile('''), "'")]
MARKUP_MASSAGE = [

4
src/libprs500/ebooks/lrf/web/__init__.py
View File

@ -16,14 +16,14 @@
import os, time, calendar, operator
from libprs500 import iswindows
from libprs500.ebooks.BeautifulSoup import BeautifulStoneSoup, BeautifulSoup
from libprs500.ebooks.BeautifulSoup import BeautifulStoneSoup
def parse_feeds(feeds, browser, print_version, max_articles_per_feed=10):
articles = {}
for title, url in feeds:
src = browser.open(url).read()
articles[title] = []
soup = BeautifulStoneSoup(src, convertEntities=BeautifulSoup.HTML_ENTITIES)
soup = BeautifulStoneSoup(src)
for item in soup.findAll('item'):
try:
pubdate = item.find('pubdate').string