From c56d37a6a78f07e73885abea07612f26f983fc25 Mon Sep 17 00:00:00 2001 From: hillerliao Date: Fri, 17 Apr 2020 20:09:19 +0800 Subject: [PATCH] add host to request header for jintiankansha --- rsshub/spiders/interotc/cpgg.py | 2 +- rsshub/spiders/jintiankansha/column.py | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/rsshub/spiders/interotc/cpgg.py b/rsshub/spiders/interotc/cpgg.py index c611645..c9386a4 100644 --- a/rsshub/spiders/interotc/cpgg.py +++ b/rsshub/spiders/interotc/cpgg.py @@ -22,7 +22,7 @@ def ctx(category=''): # req_params = {'pageSize': '10','startDate':'-1', 'keyword': category, 'pageIndex': '1'} # posts = requests.post(url, \ # data=req_params, headers=DEFAULT_HEADERS) - req_params = f'?keyword={category}&pageSize=100' + req_params = f'?keyword={category}&pageSize=150' posts = requests.get(url+req_params) import json posts = json.loads(posts.text)['resultSet'] diff --git a/rsshub/spiders/jintiankansha/column.py b/rsshub/spiders/jintiankansha/column.py index 20adfe7..645b96d 100644 --- a/rsshub/spiders/jintiankansha/column.py +++ b/rsshub/spiders/jintiankansha/column.py @@ -13,6 +13,7 @@ def parse(post): def ctx(category=''): url = f'{domain}/column/{category}' + DEFAULT_HEADERS.update({'Host': 'www.jintiankansha.me'}) tree = fetch(url, headers=DEFAULT_HEADERS) posts = tree.css('.cell.item') items = list(map(parse, posts))