From 7b551046d2b51761cece2ff32d6f5bb2bb753fce Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Fri, 25 Jul 2025 00:12:40 +0530
Subject: [PATCH] update wapo
Fix order of HTML parsing in preprocess_raw_html
---
recipes/wash_post.recipe | 2 +-
recipes/wash_post_print.recipe | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/recipes/wash_post.recipe b/recipes/wash_post.recipe
index 09e06c1177..b37a3d83cc 100644
--- a/recipes/wash_post.recipe
+++ b/recipes/wash_post.recipe
@@ -94,11 +94,11 @@ class TheWashingtonPost(BasicNewsRecipe):
]
def preprocess_raw_html(self, raw, url):
+ root = parse(raw)
if '/interactive/' in url:
return ('' + root.xpath('//h1')[0].text + '
'
'This article is supposed to be read in a browser.'
'')
- root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text)
diff --git a/recipes/wash_post_print.recipe b/recipes/wash_post_print.recipe
index 1e7a5aa9cd..1d9cf58074 100644
--- a/recipes/wash_post_print.recipe
+++ b/recipes/wash_post_print.recipe
@@ -81,11 +81,11 @@ class wapoprint(BasicNewsRecipe):
return feeds
def preprocess_raw_html(self, raw, url):
+ root = parse(raw)
if '/interactive/' in url:
return ('' + root.xpath('//h1')[0].text + '
'
'This article is supposed to be read in a browser.'
'')
- root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text)