小说信息

text.py

@@ -21,7 +21,7 @@ class SpiderBiQuGe(object):
         response = requests.get(url=target_url,headers=self.headers)
         # 获取响应
         page_text = response.text
-        return  etree.HTML(page_text)
+        return  page_text ,etree.HTML(page_text)
     # 负责写入和读取本地文件数据的
     def handler(self,file_name,novel_name,data="",mode="a",encoding="utf-8",tag="source"):
         if tag == "source":
@@ -31,7 +31,7 @@ class SpiderBiQuGe(object):
         else:
             file_dir = self.SOURCE_DIR
         os.makedirs(file_dir,exist_ok=True)
-        file_path = os.path.join(file_dir,f"{file_name.html}")
+        file_path = os.path.join(file_dir,f"{file_name}.html")
         with open(file=file_path,mode=mode,encoding=encoding) as fp:
             if mode == "a" or mode == "w":
                 fp.write(data)
@@ -42,9 +42,33 @@ class SpiderBiQuGe(object):
     def Spier_index(self):
         # 定义目标地址
         target_url = f"{self.area}/book/43278/"
-        tree = self.create_tree(target_url=target_url)
+        page_text,tree = self.create_tree(target_url=target_url)
+        novel_name = tree.xpath('//div[@class="info"]/h1/text()')[0].strip()
+        # /html/body/div[5]/div[2]/div[2]
+        novel_info = tree.xpath('//div[@class="info"]/div[2]/span')
+        author_name = novel_info[0].xpath("./text()")[0]
+        is_close = novel_info[1].xpath("./text()")[0]
+        update_time = novel_info[2].xpath("./text()")[0]
+        last_update = f'最新:{novel_info[-1].xpath("./a/text()")[0]}({self.area + novel_info[-1].xpath("./a/@href")[0]})'
+        data = f'''
+            {novel_info}
+        {author_name}
+        {is_close}
+        {update_time}
+        {last_update}
+        '''
+        print(data)
+
+        #print(self.area + novel_info[-1].xpath("./a/@href")[0])
+        #print(novel_info[-1].xpath("./a/text()")[0])
+        #print(novel_info)
+        for info in novel_info:
+            data = info.xpath("./text()")[0]
+            #print(data)
+        #print(self.area + novel_info[-1].xpath("./a/@href")[0])
+        #print(novel_info[-1].xpath("./a/text()")[0])
         #print(page_text)
-        #self.handler(file_name="index",novel_name=)
+        self.handler(file_name="index",novel_name=novel_name,data=page_text)
 if __name__ == '__main__':
     spider = SpiderBiQuGe()
     spider.Spier_index()