Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

update wapo

Browse Source 
Fix order of HTML parsing in preprocess_raw_html
This commit is contained in:
unkn0w7n 2025-07-25 00:12:40 +05:30
parent 1d2f6fd03b
commit 7b551046d2
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/wash_post.recipe
View File

@ -94,11 +94,11 @@ class TheWashingtonPost(BasicNewsRecipe):
] ]
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
root = parse(raw)
if '/interactive/' in url: if '/interactive/' in url:
return ('<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>' return ('<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>'
'This article is supposed to be read in a browser.' 'This article is supposed to be read in a browser.'
'</em></article></body></html>') '</em></article></body></html>')
root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]') m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text) data = json.loads(m[0].text)

2
recipes/wash_post_print.recipe
View File

@ -81,11 +81,11 @@ class wapoprint(BasicNewsRecipe):
return feeds return feeds
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
root = parse(raw)
if '/interactive/' in url: if '/interactive/' in url:
return ('<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>' return ('<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>'
'This article is supposed to be read in a browser.' 'This article is supposed to be read in a browser.'
'</em></article></body></html>') '</em></article></body></html>')
root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]') m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text) data = json.loads(m[0].text)