海南省国资委

REITs专题数据/policy-hainan.py

-import requests
+import time
+import time
+
 import requests
 from bs4 import BeautifulSoup
 
 import os
 import pandas as pd
 import numpy as np
+from retry import retry
+
+import BaseCore
+
+baseCore = BaseCore.BaseCore()
+log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
 
+topic = 'policy'
+webname = '海南省人民政府'
 
 headers = {
     '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',
 }
 
-
+@retry(tries=3, delay=1)
 def getSoup(url):
     ip = baseCore.get_proxy()
     req = requests.get(url, headers=headers, proxies=ip)
@@ -18,12 +32,19 @@ def getSoup(url):
         return ''
     req.encoding = req.apparent_encoding
     soup = BeautifulSoup(req.text, 'html.parser')
+    if soup:
         return soup
+    else:
+        raise Exception("重试")
+
 
 
 def getPageSize(type):
     url = f'https://www.hainan.gov.cn/s?siteCode=4600000001&searchWord=REITs&column={type}&wordPlace=0&orderBy=1&startTime=&endTime=&isSecondSearch=undefined&pageSize=10&pageNum=0&timeStamp=0&labelHN=&uc=0&checkHandle=1&strFileType=0&countKey=%200&sonSiteCode=&areaSearchFlag=&secondSearchWords=&left_right_flag=1'
+    try:
         soup = getSoup(url)
+    except:
+        return 0
     total = int(soup.find('div', class_='results-list').find('span').text.lstrip().strip())
     if total % 10 == 0:
         pageSize = int(total / 10)
@@ -33,16 +54,18 @@ def getPageSize(type):
 
 
 def getContent(url, publishDate, num):
-    fjhref_list = ''
-    fjtitle_list = ''
+    try:
         soup = getSoup(url)
+    except:
+        return '', '', ''
+    policy.paserUrl(soup, url)
     if soup == '':
-        return '','','',''
+        return '','',''
     try:
         writtenDate = soup.find('div', class_='zwgk_comr1').text.replace(' ', '').split('成文日期：')[1].split('标题')[
             0].lstrip().strip()
     except:
-        writtenDate = ''
+        writtenDate = None
     contentWithTag = soup.find('div', attrs={'id':'font'})
 
     try:
@@ -61,7 +84,7 @@ def getContent(url, publishDate, num):
         content = contentWithTag.text.lstrip().strip()
     except:
         print(url)
-    return writtenDate, content, fjtitle_list, fjhref_list
+    return writtenDate, content, contentWithTag
 
 
 def getData(div, num):
@@ -80,40 +103,62 @@ def getData(div, num):
         summary = div.find('p', class_='p-text-color').text.lstrip().strip()
     except:
         summary = ''
-    writtenDate, content, fjtitle_list, fjhref_list = getContent(href, publishDate, num)
+    writtenDate, content, contentWithTag = getContent(href, publishDate, num)
     if content == '':
-        return []
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+        return
+    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': '1729042375596158978',
+    }
+    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/海南省人民政府/政策文件'):
-        os.makedirs('./相关政策/海南省人民政府/政策文件')
-    data_list = []
-    href_list = []
     num = 1
     types = [2682,2677]
     for type in types:
         pageSize = getPageSize(type)
         for page in range(pageSize):
             url = f'https://www.hainan.gov.cn/s?siteCode=4600000001&searchWord=REITs&column={type}&wordPlace=0&orderBy=1&startTime=&endTime=&isSecondSearch=undefined&pageSize=10&pageNum={page}&timeStamp=0&labelHN=&uc=0&checkHandle=1&strFileType=0&countKey=%200&sonSiteCode=&areaSearchFlag=&secondSearchWords=&left_right_flag=1'
+            try:
                 soup = getSoup(url)
+            except:
+                continue
             div_list = soup.select('#showPage > div')
             del (div_list[-1])
             for div in div_list:
                 href = div.find('a', class_='titlec').get('href')
-                if href not in href_list:
-                    data = getData(div, num)
-                    if data:
-                        href_list.append(href)
-                        data_list.append(data)
+                # 根据链接判重
+                is_member = baseCore.r.sismember('REITs::' + webname, href)
+                if is_member:
+                    continue
+
+                getData(div, num)
                 num += 1
-                        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/海南省人民政府/江西省人民政府政策文件.xlsx', index=False)
+
 
 
 if __name__ == '__main__':