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 2017-03-17 13:15:51 +05:30
parent f10ef8fe90
commit 07a716ef38
2 changed files with 26 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/economist.recipe
View File

@ -122,15 +122,19 @@ class Economist(BasicNewsRecipe):
return br
def preprocess_raw_html(self, raw, url):
soup = self.index_to_soup(raw)
for div in soup.findAll(**classes('lazy-image')):
noscript = div.find('noscript')
if noscript is not None:
img = noscript.find('img')
if img is not None:
img.extract()
noscript.replaceWith(img)
return type(u'')(soup)
import html5lib
root = html5lib.parse(raw, namespaceHTMLElements=False, treebuilder='lxml')
from lxml import etree
for div in root.xpath('//div[@class="lazy-image"]'):
noscript = list(div.iter('noscript'))
if noscript and noscript[0].text:
img = list(html5lib.parse(noscript[0].text, namespaceHTMLElements=False, treebuilder='lxml').iter('img'))
if img:
p = noscript[0].getparent()
idx = p.index(noscript[0])
p.insert(idx, p.makeelement('img', src=img[0].get('src')))
p.remove(noscript[0])
return etree.tostring(root, encoding=unicode)
def parse_index(self):
# return [('Articles', [{'title':'test',

22
recipes/economist_free.recipe
View File

@ -122,15 +122,19 @@ class Economist(BasicNewsRecipe):
return br
def preprocess_raw_html(self, raw, url):
soup = self.index_to_soup(raw)
for div in soup.findAll(**classes('lazy-image')):
noscript = div.find('noscript')
if noscript is not None:
img = noscript.find('img')
if img is not None:
img.extract()
noscript.replaceWith(img)
return type(u'')(soup)
import html5lib
root = html5lib.parse(raw, namespaceHTMLElements=False, treebuilder='lxml')
from lxml import etree
for div in root.xpath('//div[@class="lazy-image"]'):
noscript = list(div.iter('noscript'))
if noscript and noscript[0].text:
img = list(html5lib.parse(noscript[0].text, namespaceHTMLElements=False, treebuilder='lxml').iter('img'))
if img:
p = noscript[0].getparent()
idx = p.index(noscript[0])
p.insert(idx, p.makeelement('img', src=img[0].get('src')))
p.remove(noscript[0])
return etree.tostring(root, encoding=unicode)
def parse_index(self):
# return [('Articles', [{'title':'test',