黑龙江省人民政府

REITs专题数据/policy-heilongjiang.py

-import os
+#coding=utf-8
+#coding=utf-8
 import os
 import time
 
-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 = '黑龙江省人民政府'
 headers = {
     'Content-Type': 'application/x-www-form-urlencoded',
-    'Token': 'db345f2c-20fd-4cc8-9799-b9cd08b96392',
+    'Token': '9a9ff46e-f534-43b8-bad1-063d80af7e51',
     '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',
 }
 
@@ -34,10 +39,11 @@ def getDataJson():
 
 
 def getSoup(url):
-    ip = baseCore.get_proxy()
-    req = requests.get(url,headers=headers,proxies=ip)
+    # ip = baseCore.get_proxy()
+    req = requests.get(url, headers=headers)
     req.encoding = req.apparent_encoding
-    soup = BeautifulSoup(req.json()['content']['html'],'lxml')
+    print(req.json())
+    soup = BeautifulSoup(req.json()['content']['html'], 'lxml')
     return soup
 
 
@@ -49,10 +55,9 @@ def getFjContent(url):
 
 
 def getContent(num, title, publishDate, summary, id, pub_hao, organ,type):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     url = f'https://www.hlj.gov.cn/znwd/policy/#/readDetails?id={id}'
-    writtenDate = ''
+    writtenDate = None
     if type == '政策解读':
         origin = organ
         organ = ''
@@ -60,7 +65,10 @@ def getContent(num, title, publishDate, summary, id, pub_hao, organ,type):
     else:
         origin = '黑龙江省人民政府'
         href_ = f'https://www.hlj.gov.cn/znwd/policy/policy/policy/ctrl/public/chatPolicyFile/findById/{id}'
-
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, url)
+    if is_member:
+        return
     soup = getSoup(href_)
     try:
         a_list = soup.find_all('a')
@@ -68,19 +76,17 @@ def getContent(num, title, publishDate, summary, id, pub_hao, organ,type):
             href = a.get('href')
             if '.html' in href or '.shtml' in href or '.htm' in href:
                 continue
-            fjhref_list += href + '\n'
+
             category = os.path.splitext(href)[1]
-            fj_title = f'{num}-{publishDate}-{a.text.lstrip().strip()}'
+            fj_title = a.text.lstrip().strip()
             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/黑龙江省人民政府/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')
+            att_id, full_path = policy.attuributefile(fj_title,href,num,publishDate)
+            if att_id:
+                id_list.append(att_id)
+                a['href'] = full_path
     except Exception as e:
         log.error(title, '=====', e)
     try:
@@ -96,15 +102,39 @@ def getContent(num, title, publishDate, summary, id, pub_hao, organ,type):
     except:
         pass
     content = soup.text.lstrip().strip()
-    data_ = [num, title, writtenDate, origin, url, publishDate, organ, pub_hao, summary, content, fjtitle_list,
-             fjhref_list]
-    return data_
+    contentWithTag_str = str(soup)
+    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': '1729042585839841281',
+    }
+    try:
+        baseCore.sendkafka(dic_info, topic)
+        baseCore.r.sadd('REITs::' + webname, url)
+        log.info(f'采集成功--{title}--{url}')
+    except Exception as e:
+        for att_id in id_list:
+            baseCore.deliteATT(att_id)
+    return
 
 
 def doJob():
-    if not os.path.exists('./相关政策/黑龙江省人民政府/政策文件'):
-        os.makedirs('./相关政策/黑龙江省人民政府/政策文件')
-    data_list = []
+
     num = 1
     data_json = getDataJson()
     for data_ in data_json:
@@ -122,12 +152,10 @@ def doJob():
         except:
             organ = ''
         data = getContent(num, title, publishDate, summary, id, pub_hao, organ,type)
-        data_list.append(data)
+        # data_list.append(data)
         num += 1
         time.sleep(3)
-    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/黑龙江省人民政府/黑龙江省人民政府政策文件.xlsx', index=False)
+
 
 if __name__ == "__main__":
     doJob()