From 53e055637a85191cf88987740eeedb7bdb8204af Mon Sep 17 00:00:00 2001 From: hillerliao Date: Thu, 11 Aug 2022 18:08:04 +0800 Subject: [PATCH 1/2] try to fix aisixiang encoding bug in vercel.app --- rsshub/spiders/aisixiang/search.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/rsshub/spiders/aisixiang/search.py b/rsshub/spiders/aisixiang/search.py index d392519..3093f59 100644 --- a/rsshub/spiders/aisixiang/search.py +++ b/rsshub/spiders/aisixiang/search.py @@ -1,4 +1,4 @@ -import urllib.parse +from urllib.parse import quote, unquote from rsshub.utils import fetch, DEFAULT_HEADERS @@ -14,8 +14,9 @@ def parse(post): def ctx(category='', keywords=''): - keywords_encode = urllib.parse.quote(keywords, encoding='gbk') - url = f"{domain}/data/search.php?keyWords={keywords_encode}&searchfield={category}" + keywords = unquote(keywords,encoding='utf-8') + keywords_gbk = quote(keywords, encoding='gbk') + url = f"{domain}/data/search.php?keyWords={keywords_gbk}&searchfield={category}" tree = fetch(url, headers=DEFAULT_HEADERS) posts = tree.css('.search_list').css('li') return { From 25b0cfd9389b4b8a8dde0f7885f108f7b20be33d Mon Sep 17 00:00:00 2001 From: hillerliao Date: Wed, 7 Sep 2022 18:22:04 +0800 Subject: [PATCH 2/2] fix world brief bug --- rsshub/spiders/economist/worldbrief.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/rsshub/spiders/economist/worldbrief.py b/rsshub/spiders/economist/worldbrief.py index 5584ecc..d1803a8 100644 --- a/rsshub/spiders/economist/worldbrief.py +++ b/rsshub/spiders/economist/worldbrief.py @@ -6,9 +6,9 @@ domain = 'https://www.economist.com' def parse(post): item = {} - item['title'] = post.css('div.e18qdnq10').get() - item['title'] = re.sub(r'<[^>]*>', '', item['title']).strip() + item['title'] = post.css('div').css('p').get() item['description'] = item['title'] + item['title'] = re.sub(r'<[^>]*>', '', item['title']).strip() item['link'] = f"{domain}/the-world-in-brief" + '?from=' + item['title'][:30] return item