重庆市人民政府

REITs专题数据/policy-chongqing.py

-import json
+import json
@@ -3,13 +3,18 @@ import time
 
 import requests
 from bs4 import BeautifulSoup
-from base import BaseCore
-import os
-import pandas as pd
-import numpy as np
+
+import BaseCore
 
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
+
+topic = 'policy'
+webname = '重庆市人民政府'
 headers = {
     'Content-Type': 'application/json',
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0',
@@ -112,8 +117,10 @@ def getContent(url):
         id = url.split('policyId=')[1]
         contentWithTag  = getContent_(id)
         contentWithTag = BeautifulSoup(contentWithTag,'lxml')
+        policy.paserUrl(contentWithTag, url)
     else:
         soup = getSoup(url)
+        policy.paserUrl(soup, url)
         contentWithTag = soup.find('div', class_='view')
         if not contentWithTag:
             contentWithTag = soup.find('div',class_='document')
@@ -131,7 +138,7 @@ def getContent(url):
     except:
         pass
     content = contentWithTag.text.lstrip().strip()
-    return content
+    return content, contentWithTag
 
 
 def getData(data_, num):
@@ -139,6 +146,11 @@ def getData(data_, num):
     publishDate = data_['save_time']
     origin = data_['f_2021325755960']
     href = data_['doc_pub_url']
+
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     try:
         writtenDate = data_['f_202121607647']
     except:
@@ -153,31 +165,47 @@ def getData(data_, num):
         pub_hao = ''
     summary = data_['f_202142777829']
     summary = BeautifulSoup(summary, 'lxml').text.lstrip().strip()
-    content = getContent(href)
-    fjtitle_list = ''
-    fjhref_list = ''
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    content, contentWithTag = getContent(href)
+    contentWithTag_str = str(contentWithTag)
+    time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+    dic_info = {
+        'attachmentIds': [],
+        'author': '',
+        'content': content,
+        'contentWithTag': contentWithTag_str,
+        'deleteFlag': 0,
+        'id': '',
+        'title': title,
+        'publishDate': publishDate,
+        'origin': origin,
+        'sourceAddress': href,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729045755020103681',
+    }
 
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, href)
+        log.info(f'采集成功--{title}--{href}')
+    except Exception as e:
+        return
+    return
 
 def doJob():
-    if not os.path.exists('./相关政策/重庆市人民政府/政策文件'):
-        os.makedirs('./相关政策/重庆市人民政府/政策文件')
+
     total = getTotal()
     num = 1
-    data_list = []
     for page in range(1, total + 1):
         data_json = getDataJson(page)
         for data_ in data_json:
-            data = getData(data_, num)
+            getData(data_, num)
             num += 1
             time.sleep(3)
-            data_list.append(data)
-            log.info(f'{data[1]}===采集成功')
-    df = pd.DataFrame(np.array(data_list))
-    df.columns = ['序号', '标题', '发布时间', '来源', '原文链接', '发文时间', '发文机构', '发文字号', '摘要', '正文', '附件名称', '附件连接']
-    df.to_excel('./相关政策/重庆市人民政府/重庆市人民政府政策文件.xlsx', index=False)
 
 
 if __name__ == '__main__':