山东省人民政府

REITs专题数据/policy-shandong.py

-import time
+import time
@@ -2,13 +2,17 @@ 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 = '山东省人民政府'
 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',
     'X-Requested-With': 'XMLHttpRequest',
@@ -55,8 +59,7 @@ def getDataJson(page):
 
 
 def getContent(url, publishDate, num):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     soup = getSoup(url)
     contentWithTag = soup.find('div', class_='wip_art_con')
     a_list = contentWithTag.find_all('a')
@@ -65,7 +68,7 @@ def getContent(url, publishDate, num):
         fj_href = a.get('href')
         if 'http' not in fj_href:
             fj_href = 'http://www.shandong.gov.cn' + fj_href
-        fjhref_list += fj_href + '\n'
+
         fj_title = a.text.lstrip().strip().replace(' ', '')
         if fj_title == '':
             fj_title = str(num_)
@@ -73,13 +76,10 @@ def getContent(url, publishDate, num):
         category = os.path.splitext(fj_href)[1]
         if category not in fj_title:
             fj_title = fj_title + category
-        fj_title = f'{num}-{publishDate}-{fj_title}'
-        fjtitle_list += fj_title + '\n'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/山东省人民政府/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, fj_href, num, publishDate)
+        if att_id:
+            id_list.append(att_id)
+            a['href'] = full_path
     try:
         scripts = contentWithTag.find_all('script')
         for script in scripts:
@@ -93,13 +93,13 @@ def getContent(url, publishDate, num):
     except:
         pass
     content = contentWithTag.text.lstrip().strip()
-    return content, fjtitle_list, fjhref_list
+    return content, contentWithTag, id_list
 
 
 def getData(soup, num):
     origin = '山东省人民政府'
     organ = ''
-    writtenDate = ''
+    writtenDate = None
     pub_hao = ''
     try:
         type = soup.find('span', class_='szf_lmmc').text
@@ -111,6 +111,11 @@ def getData(soup, num):
                 -1].text.lstrip().strip()
             pub_hao = soup.find('table', class_='szf_xxgk').find_all('tr')[1].find_all('td')[-1].text.lstrip().strip()
             href = soup.find('a', class_='szf_url').text.lstrip().strip()
+            # 根据链接判重
+            is_member = baseCore.r.sismember('REITs::' + webname, href)
+            if is_member:
+                return
+
             publishDate = soup.find('span', class_='szf_rq').text.lstrip().strip()
         else:
             summary = soup.find('div', class_='szf_ms').text.lstrip().strip()
@@ -121,16 +126,40 @@ def getData(soup, num):
         summary = soup.find('div', class_='jcse-news-abs-content').text.lstrip().strip()
         href = soup.find('div', class_='jcse-news-url').text.lstrip().strip()
         publishDate = soup.find('span', class_='jcse-news-date').text.lstrip().strip()
-    content, fjtitle_list, fjhref_list = getContent(href, publishDate, num)
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    content, contentWithTag, id_list = getContent(href, publishDate, num)
+
+    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': href,
+        'writtenDate': writtenDate,
+        'organ': organ,
+        'topicClassification': '',
+        'issuedNumber': pub_hao,
+        'summary': summary,
+        'createDate': time_now,
+        'sid': '1729043593615560705',
+    }
+    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:
+        for att_id in id_list:
+            baseCore.deliteATT(att_id)
+    return
 
 
 def doJob():
-    if not os.path.exists('./相关政策/山东省人民政府/政策文件'):
-        os.makedirs('./相关政策/山东省人民政府/政策文件')
-    data_list = []
     num = 1
     for page in range(1, 3):
         data_json = getDataJson(page)
@@ -138,13 +167,7 @@ def doJob():
             data_ = data_.replace('\\', '')
             soup = BeautifulSoup(data_, 'lxml')
             data = getData(soup, num)
-            data_list.append(data)
-            log.info(f'{data[1]}===采集成功')
             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/山东省人民政府/山东省人民政府政策文件.xlsx', index=False)
 
 
 if __name__ == '__main__':