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

IGN:Make downloading from web a little more robust

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-01 22:03:26 -08:00
parent 8a2f2f2510
commit 13ef549864
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/web/fetch/simple.py
View File

@ -15,7 +15,7 @@ from PIL import Image
from cStringIO import StringIO
from calibre import setup_cli_handlers, browser, sanitize_file_name, \
relpath, LoggingInterface
relpath, LoggingInterface, unicode_path
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
from calibre.ebooks.chardet import xml_to_unicode
from calibre.utils.config import OptionParser
@ -53,7 +53,7 @@ def save_soup(soup, target):
nm = ns.find('meta')
metas = soup.findAll('meta', content=True)
for meta in metas:
if 'charset' in meta['content']:
if 'charset' in meta.get('content', '').lower():
meta.replaceWith(nm)
selfdir = os.path.dirname(target)
@ -62,7 +62,7 @@ def save_soup(soup, target):
for key in ('src', 'href'):
path = tag.get(key, None)
if path and os.path.isfile(path) and os.path.exists(path) and os.path.isabs(path):
tag[key] = relpath(path, selfdir).replace(os.sep, '/')
tag[key] = unicode_path(relpath(path, selfdir).replace(os.sep, '/'))
html = unicode(soup)
with open(target, 'wb') as f:
@ -227,7 +227,7 @@ class RecursiveFetcher(object, LoggingInterface):
return True
def process_stylesheets(self, soup, baseurl):
diskpath = os.path.join(self.current_dir, 'stylesheets')
diskpath = unicode_path(os.path.join(self.current_dir, 'stylesheets'))
if not os.path.exists(diskpath):
os.mkdir(diskpath)
for c, tag in enumerate(soup.findAll(lambda tag: tag.name.lower()in ['link', 'style'] and tag.has_key('type') and tag['type'].lower() == 'text/css')):
@ -280,7 +280,7 @@ class RecursiveFetcher(object, LoggingInterface):
def process_images(self, soup, baseurl):
diskpath = os.path.join(self.current_dir, 'images')
diskpath = unicode_path(os.path.join(self.current_dir, 'images'))
if not os.path.exists(diskpath):
os.mkdir(diskpath)
c = 0