Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

jsbrowser: Fix handling of html with non lxml safe chars

Browse Source
This commit is contained in:
Kovid Goyal 2013-07-09 14:44:46 +05:30
parent c4cb0e445e
commit a94539c32b
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/web/fetch/javascript.py
View File

@ -145,8 +145,11 @@ def download_resources(browser, resource_cache, output_dir):
elem.removeFromDocument() elem.removeFromDocument()
def save_html(browser, output_dir, postprocess_html, url, recursion_level): def save_html(browser, output_dir, postprocess_html, url, recursion_level):
html = strip_encoding_declarations(browser.html)
import html5lib import html5lib
from calibre.utils.cleantext import clean_xml_chars
html = strip_encoding_declarations(browser.html)
if isinstance(html, unicode):
html = clean_xml_chars(html)
root = html5lib.parse(html, treebuilder='lxml', namespaceHTMLElements=False).getroot() root = html5lib.parse(html, treebuilder='lxml', namespaceHTMLElements=False).getroot()
root = postprocess_html(root, url, recursion_level) root = postprocess_html(root, url, recursion_level)
if root is None: if root is None: