四川省人民政府

REITs专题数据/policy-sichuan.py

-import requests
+import time
+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 = '四川省人民政府'
 headers = {
     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
     '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',
@@ -51,84 +60,87 @@ def getDataJson():
 
 
 def getContent(url, publishDate, num):
-    url_ = url.split('/')[-1]
-    url_ = url.replace(url_, '')
-    fjhref_list = ''
-    fjtitle_list = ''
+
     soup = getSoup(url)
+    policy.paserUrl(soup, url)
     try:
         writtenDate = \
         soup.select('#szfcontentwrap2022 > div.zfwjwzcontent > div.topbox > ul > li')[3].text.split('成文日期：')[
             1].lstrip().strip()
     except:
-        writtenDate = ''
+        writtenDate = None
     try:
         contentWithTag = soup.select('.contText')[0]
     except:
         contentWithTag = soup.select('#cmsArticleContent')[0]
-    img_list = contentWithTag.find_all('img')
-    num_ = 1
-    for img in img_list:
-        fj_href = url_ + img.get('src')
-        fjhref_list += fj_href + '\n'
-        fj_title = str(num_)
-        num_ += 1
-        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/四川省人民政府/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
-    fjtitle_list = fjtitle_list.lstrip().strip()
-    fjhref_list = fjhref_list.lstrip().strip()
-    return writtenDate, content, fjtitle_list, fjhref_list
+
+    return writtenDate, content, contentWithTag
 
 
 def getData(data_, num):
+    id_list = []
     title = data_['data']['title']
     publishDate = data_['data']['docDate']
     origin = data_['data']['siteLabel']['value']
     href = data_['data']['url']
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     organ = data_['data']['myValues']['DOCPUBNAME']
     pub_hao = data_['data']['myValues']['DOCNOVAL']
     summary = ''
     if '.pdf' in href or '.PDF' in href:
         content = ''
-        writtenDate = ''
-        fjtitle_list = title + '.pdf'
-        fjhref_list = href
-        fjcontent = getFjContent(href)
-        file = f'./相关政策/四川省人民政府/政策文件/{title}.pdf'
-        with open(file, 'wb') as f:
-            f.write(fjcontent)
-        log.info(f'{title}===附件下载成功')
+        contentWithTag_str = ''
+        writtenDate = None
+        fj_title = title + '.pdf'
+        fj_href = href
+        att_id, full_path = policy.attuributefile(fj_title, fj_href, num, publishDate)
+        if att_id:
+            id_list.append(att_id)
+
     else:
-        writtenDate, 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
+        writtenDate, content, contentWithTag = 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': '1729046053927178241',
+    }
+    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/四川省人民政府/政策文件'):
-        os.makedirs('./相关政策/四川省人民政府/政策文件')
-    data_list = []
     num = 1
     data_json = getDataJson()
     for data_ in data_json:
-        data = getData(data_, num)
-        data_list.append(data)
-        log.info(f'{data[1]}===采集成功')
+        getData(data_, num)
         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('./相关政策/四川省人民政府/四川省人民政府政策文件.xlsx', index=False)
-
 
 if __name__ == '__main__':
     doJob()