山西省人民政府

REITs专题数据/policy-shanxi.py

-import os
+import os
 import os
+import time
 from urllib.parse import urljoin
 
 import numpy as np
 import pandas as pd
 import requests
 from bs4 import BeautifulSoup
-from base import BaseCore
-
+import BaseCore
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
+
+topic = 'policy'
+webname = '山西省人民政府'
 headers = {
     'Accept': 'application/json, text/plain, */*',
     'Accept-Encoding': 'gzip, deflate',
@@ -74,8 +81,7 @@ def getFjContent(url):
 
 
 def getContent(num, data):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     title = data['title']
     pub_hao = data['docno']
     origin = data['sitedesc']
@@ -84,6 +90,10 @@ def getContent(num, data):
     writtenDate = data['scrq']
     summary = BeautifulSoup(data['zc_doccontent'], 'html.parser').text.lstrip().strip()
     url = data['docpuburl']
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, url)
+    if is_member:
+        return
     url_ = url.split('/')[-1]
     soup = getSoup(url)
     soup = paserUrl(soup, url.replace(url_, ''))
@@ -102,44 +112,65 @@ def getContent(num, data):
             style.decompose()
     except:
         pass
+    content = contentWithTag.text.lstrip().strip()
     a_list = contentWithTag.find_all('a')
     for a in a_list:
         href = a.get('href')
-        fjhref_list += href + '\n'
+
         category = os.path.splitext(href)[1]
-        fj_title = f'{num}-{publishDate}-{a.text.lstrip().strip()}'
+        fj_title = a.text.lstrip()
         if '<' in fj_title or '>' in fj_title:
             fj_title = fj_title.replace('<', '').replace('>', '')
         if category not in fj_title:
             fj_title = fj_title + category
-        fjtitle_list += fj_title + '\n'
-        fjcontent = getFjContent(href)
-        file = f'./相关政策/山西省人民政府/政策文件/{fj_title}'
-        with open(file, 'wb') as f:
-            f.write(fjcontent)
-        log.info(f'{fj_title}===附件下载成功')
-    content = contentWithTag.text.lstrip().strip()
-    data_ = [num, title, writtenDate, origin, url, publishDate, organ, pub_hao, summary, content, fjtitle_list, fjhref_list]
-    return data_
+
+        att_id, full_path = policy.attuributefile(fj_title, href, num, publishDate)
+        if att_id:
+            id_list.append(att_id)
+            a['href'] = full_path
+    contentWithTag_str = str(contentWithTag)
+    time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+    dic_info = {
+        'attachmentIds': id_list,
+        'author': '',
+        'content': content,
+        'contentWithTag': contentWithTag_str,
+        'deleteFlag': 0,
+        'id': '',
+        'title': title,
+        'publishDate': publishDate,
+        'origin': origin,
+        'sourceAddress': url,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729041791539326977',
+    }
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, url)
+        log.info(f'采集成功--{title}--{url}')
+    except:
+        for att_id in id_list:
+            baseCore.deliteATT(att_id)
+    return
 
 
 def doJob():
-    if not os.path.exists('./相关政策/山西省人民政府/政策文件'):
-        os.makedirs('./相关政策/山西省人民政府/政策文件')
+
     num = 1
-    data_list = []
+    # data_list = []
     pageSize = getPageSize()
     for page in range(1, pageSize + 1):
         data_json = getJson(page)
         for i in range(len(data_json)):
             if data_json[i]['chnldesc'] == '政策文件':
-                data = getContent(num, data_json[i])
-                data_list.append(data)
-                log.info(f'{data[1]}===采集成功')
+                getContent(num, data_json[i])
                 num += 1
-    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('./山西省人民政府政策文件.xlsx', index=False)
+
 
 
 if __name__ == '__main__':