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

...

Browse Source
This commit is contained in:
Kovid Goyal 2015-09-12 18:46:09 +05:30
parent 47dce862cc
commit 2af36a378b
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
recipes/natgeo.recipe
View File

@ -2,6 +2,7 @@
# vim:fileencoding=utf-8 # vim:fileencoding=utf-8
from __future__ import (unicode_literals, division, absolute_import, from __future__ import (unicode_literals, division, absolute_import,
print_function) print_function)
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag from calibre.ebooks.BeautifulSoup import Tag
import html5lib import html5lib
@ -40,6 +41,10 @@ class NatGeo(BasicNewsRecipe):
def preprocess_raw_html(self, raw_html, url): def preprocess_raw_html(self, raw_html, url):
# BeautifulSoup does not parse the natgeo html correctly, so we use a # BeautifulSoup does not parse the natgeo html correctly, so we use a
# custom cleanup routine # custom cleanup routine
# NatGeo embeds huge inline svg images as interactive graphics, this
# breaks conversion because split points cannot be found
raw_html = re.sub(r'<svg.+?</svg>', '', raw_html, flags=re.DOTALL)
root = html5lib.parse(raw_html, namespaceHTMLElements=False, treebuilder='lxml') root = html5lib.parse(raw_html, namespaceHTMLElements=False, treebuilder='lxml')
select = Select(root) select = Select(root)
keep = tuple(select('.mainArt')) + tuple(select('.byline')) + tuple(select('#article__body')) keep = tuple(select('.mainArt')) + tuple(select('.byline')) + tuple(select('#article__body'))