d0zingcat/RSSHub-python
1
0
Fork 0
mirror of https://github.com/d0zingcat/RSSHub-python.git synced 2026-05-19 15:09:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix weiyangx tag list

Browse Source
This commit is contained in:
hillerliao
2020-04-25 22:28:04 +08:00
parent d6f2bc9c86
commit bf14280a80
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
rsshub/spiders/weiyangx/tag.py
View File

@@ -1,21 +1,27 @@
from rsshub.utils import DEFAULT_HEADERS from rsshub.utils import DEFAULT_HEADERS
from rsshub.utils import fetch import requests
import json
from parsel import Selector
domain = 'https://www.weiyangx.com' domain = 'https://www.weiyangx.com'
def parse(post): def parse(post):
item = {} item = {}
item['title'] = post.css('h2::text').extract_first() item['title'] = post['post_title']
item['description'] = post.css('p::text').extract_first() item['description'] = post['post_content']
item['link'] = post.css('a::attr(href)').extract_first() post_id = post['post_id']
item['link'] = f'{domain}/{post_id}.html'
return item return item
def ctx(category=''): def ctx(category=''):
url = f'https://www.weiyangx.com/tag/{category}' url = f'https://www.weiyangx.com/tag/{category}'
tree = fetch(url, headers=DEFAULT_HEADERS) res = requests.get(url, headers=DEFAULT_HEADERS)
posts = tree.css('.category-post-node') res = Selector(res.text)
posts = res.css('script::text')[-4].extract().split('=')[-1]
posts = json.loads(posts)
# posts = tree.css('script::text')[-5].extract().split('=')[-1]
items = list(map(parse, posts)) items = list(map(parse, posts))
return { return {
'title': f'{category} - 文章 - 未央网', 'title': f'{category} - 文章 - 未央网',