add home list

rsshub/blueprints/main.py

@@ -121,6 +121,11 @@ def techcrunch_tag(category=''):
     from rsshub.spiders.techcrunch.tag import ctx
     return render_template('main/atom.xml', **filter_content(ctx(category)))
 
+@bp.route('/weiyangx/home')
+def weiyangx_home():
+    from rsshub.spiders.weiyangx.home import ctx
+    return render_template('main/atom.xml', **filter_content(ctx()))
+
 @bp.route('/weiyangx/express/')
 def weiyangx_express():
     from rsshub.spiders.weiyangx.express import ctx

rsshub/spiders/weiyangx/express.py

@@ -1,5 +1,6 @@
 import requests
 import json
+from parsel import Selector
 from rsshub.utils import DEFAULT_HEADERS
 
 domain = 'https://www.weiyangx.com'
@@ -18,14 +19,11 @@ def parse(post):
 
 
 def ctx():
-    url = f'https://www.weiyangx.com/wp-admin/admin-ajax.php'
-    q_data = {"action": "load_more_express",
-              "offset": "00",
-              "category": "29817",
-              "_ajax_nonce": "235111d38c"}
-
-    res = requests.post(url, data=q_data, headers=DEFAULT_HEADERS)
-    posts = json.loads(res.text)['expressList']
+    url = f'https://www.weiyangx.com/category/express'
+    res = requests.get(url, headers=DEFAULT_HEADERS)
+    res = Selector(res.text)
+    posts = res.css('script::text')[-4].extract().split('=')[-1]
+    posts = json.loads(posts)
     items = list(map(parse, posts))
     return {
         'title': f'快讯 - 未央网',

rsshub/spiders/weiyangx/home.py

@@ -0,0 +1,31 @@
+import requests
+import json
+from parsel import Selector
+from rsshub.utils import DEFAULT_HEADERS
+
+domain = 'https://www.weiyangx.com'
+
+
+def parse(post):
+    item = {}
+    item['title'] = post['title']
+    item['description'] = post['content']
+    post_id = post['id']
+    item['link'] = f'{domain}/{post_id}.html'
+    return item
+
+
+def ctx():
+    url = f'https://www.weiyangx.com/'
+    res = requests.get(url, headers=DEFAULT_HEADERS)
+    res = Selector(res.text)
+    posts = res.css('script::text')[-5].extract().split('=')[-1]
+    posts = json.loads(posts)
+    items = list(map(parse, posts))
+    return {
+        'title': f'快讯 - 未央网',
+        'description': f'快讯 - 未央网',
+        'link': f'{domain}/category/express',
+        'author': f'hillerliao',
+        'items': items
+    }

rsshub/spiders/weiyangx/tag.py

@@ -1,28 +1,21 @@
-import requests
-import json
 from rsshub.utils import DEFAULT_HEADERS
+from rsshub.utils import fetch
 
 domain = 'https://www.weiyangx.com'
 
 
 def parse(post):
     item = {}
-    item['title'] = post['title']
-    item['description'] = post['content']
-    item['link'] = post['url']
-    item['author'] = post['authorMeta']
+    item['title'] = post.css('h2::text').extract_first()
+    item['description'] = post.css('p::text').extract_first()
+    item['link'] = post.css('a::attr(href)').extract_first()
     return item
 
 
 def ctx(category=''):
-    url = f'https://www.weiyangx.com/wp-admin/admin-ajax.php'
-    q_data = {"action": "home_load_more_news",
-              "postOffset": "00",
-              "tagId": category,
-              "_ajax_nonce": "1846edad4e"}
-
-    res = requests.post(url, data=q_data, headers=DEFAULT_HEADERS)
-    posts = json.loads(res.text)['data']
+    url = f'https://www.weiyangx.com/tag/{category}'
+    tree = fetch(url, headers=DEFAULT_HEADERS)
+    posts = tree.css('.category-post-node')
     items = list(map(parse, posts))
     return {
         'title': f'{category} - 文章 - 未央网',