添加知乎 (www.zhihu.com) 的两个频道： 圆桌和收藏夹

rsshub/spiders/zhihu/article.py

@@ -40,6 +40,10 @@ class ZhihuAnswer(AtomEntry):
         self.content = zhihu_figure_transfer(tree.css('.RichText').get())
         self.description = self.content
 
+        # author
+
+        self.author = json.loads(tree.xpath('//div[@class="ContentItem AnswerItem"]/@data-zop').get())['authorName']
+
         meta: dict = get_value(json.loads(tree.css("#js-initialData::text").get())
                                ['initialState']['entities']['questions'])
 
@@ -51,9 +55,18 @@ class ZhihuZhuanlanArticle(AtomEntry):
     def get(self):
         tree = fetch(self.link)
         self.title = tree.css('h1::text').get()
+        author = tree.xpath('//meta[@itemProp="name"]/@content').get()
+        if author:
+            self.author = author
         self.content = zhihu_figure_transfer(tree.css('article').css('.RichText').get())
         self.description = self.content
 
+        #
+        data = json.loads(tree.css("#js-initialData::text").get())
+        metadata = list(data['initialState']['entities']['articles'].values())[0]
+        self.pubDate = datetime.fromtimestamp(metadata['created'])
+        self.updated_time = datetime.fromtimestamp(metadata['updated'])
+
 
 class ZhihuQuestion(Feed):
 

rsshub/spiders/zhihu/collection.py

@@ -0,0 +1,44 @@
+import json
+import requests
+
+from .article import ZhihuAnswer, ZhihuZhuanlanArticle
+
+
+
+def get_metadata(collection_id):
+    response = requests.get(f'https://api.zhihu.com/collections/{collection_id}')
+    response.raise_for_status()
+    data = json.loads(response.text)['collection']
+
+    metadata = dict()
+    metadata['link'] = data['url']
+    metadata['title'] = data['title']
+    # metadata['created_time'] = data['created_time']
+    # metadata['updated_time'] = data['updated_time']
+    return metadata
+
+def ctx(collection_id):
+
+    # meta
+    metadata = get_metadata(collection_id)
+
+    # content
+
+    response = requests.get(f'https://www.zhihu.com/api/v4/collections/{collection_id}/items?limit=20&offset=0')
+    response.raise_for_status()
+    data = json.loads(response.text)
+    items = []
+
+    for d in data['data']:
+        if d['content']['type'] == 'answer':
+            item = ZhihuAnswer(d['content']['url'])
+        elif d['content']['type'] == 'article':
+            item = ZhihuZhuanlanArticle(d['content']['url'])
+        else:
+            assert False
+        item.get()
+        items.append(item)
+
+    metadata['items'] = items
+
+    return metadata

rsshub/spiders/zhihu/explore.py

@@ -14,7 +14,7 @@ def ctx():
     discussion = tree.css('.ExploreRoundtableCard-questionTitle')
     collection_card = tree.css('.ExploreCollectionCard-contentTitle')
 
-    for post in chain(hot_question, collection_card, discussion, newest_topic):
+    for post in chain(hot_question, collection_card, discussion): #, newest_topic):
         title = post.css('a::text').extract_first()
         link: str = post.css('a::attr(href)').extract_first()
 

rsshub/spiders/zhihu/roundtable.py

@@ -0,0 +1,23 @@
+import json
+import requests
+
+from .article import ZhihuQuestion
+
+def ctx(name):
+    url = f'https://www.zhihu.com/api/v4/roundtables/{name}/hot-questions?include=data[*].question.relationship'
+    response = requests.get(url)
+    response.raise_for_status()
+
+    data = json.loads(response.text)
+    items = []
+
+    for d in data['data']:
+        item = ZhihuQuestion(f'https://www.zhihu.com/question/{d["question"]["id"]}')
+        item.get_description()
+
+        items.append(item)
+
+    return {
+        'title': 'roundtable',
+        'items': items
+    }