广东省人民政府

REITs专题数据/policy-guangdong.py

-import datetime
+import datetime
@@ -6,13 +6,21 @@ import requests
 from bs4 import BeautifulSoup
 from retry import retry
 
-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 = '广东省人民政府'
 headers = {
     'Content-Type': 'application/json',
     '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',
@@ -65,10 +73,10 @@ def getDataJson(url, data_post):
 
 
 def getContent(url, publishDate, num):
-    fjhref_list = ''
-    fjtitle_list = ''
+    id_list = []
     soup = getSoup(url)
     time.sleep(2)
+    policy.paserUrl(soup, url)
     try:
         try:
             contentWithTag = soup.select('body > div.con > div.viewList > div.zw')[0]
@@ -78,54 +86,21 @@ def getContent(url, publishDate, num):
         contentWithTag = soup.find('div', class_='article-content').find('center')
         if not contentWithTag:
             contentWithTag = soup.find('div', class_='article-content')
-    img_list = contentWithTag.find_all('img')
-    num_ = 1
-    for img in img_list:
-        fj_href = img.get('src')
-        if "http" not in fj_href and '//www' in fj_href:
-            fj_href = 'http:' + fj_href
-        fjhref_list += fj_href + '\n'
-        fj_title = img.get('alt')
-        if fj_title == '':
-            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}'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/广东省人民政府/政策文件/{fj_title}'
-        if os.path.exists(file):
-            file = file.replace(category, f'-{num_}{category}')
-            num_ += 1
-        if os.path.exists(file):
-            fj_title = fj_title.replace(category, f'-{num_}{category}')
-            file = f'./相关政策/广东省人民政府/政策文件/{fj_title}'
-        fjtitle_list += fj_title + '\n'
-        with open(file, 'wb') as f:
-            f.write(fjcontent)
-        log.info(f'{fj_title}===附件下载成功')
+
     a_list = contentWithTag.find_all('a')
     for a in a_list:
         fj_href = a.get('href')
-        fjhref_list += fj_href + '\n'
+
         fj_title = a.text.lstrip().strip()
         if fj_title == '':
-            fj_title = str(num_)
-            num_ += 1
+            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}'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/广东省人民政府/政策文件/{fj_title}'
-        if os.path.exists(file):
-            file = file.replace(category, f'-{num_}{category}')
-            num_ += 1
-        fjtitle_list += fj_title + '\n'
-        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)
     try:
         scripts = contentWithTag.find_all('script')
         for script in scripts:
@@ -139,9 +114,8 @@ def getContent(url, publishDate, num):
     except:
         pass
     content = contentWithTag.text.lstrip().strip()
-    fjtitle_list = fjtitle_list.lstrip().strip()
-    fjhref_list = fjhref_list.lstrip().strip()
-    return content, fjtitle_list, fjhref_list
+
+    return content, contentWithTag, id_list
 
 
 def ST(txt):
@@ -149,12 +123,17 @@ def ST(txt):
     return txt
 
 
-def getData(data_, num):
+def getData(data_, num,sid):
     title = ST(data_['title'])
     log.info(f'{title}===开始采集')
     publishDate = data_['pub_time']
     origin = data_['publisher_src']
     href = data_['url']
+
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
     log.info(href)
     writtenDate = data_['date']
     if writtenDate:
@@ -162,17 +141,44 @@ def getData(data_, num):
     organ = data_['source']
     pub_hao = data_['document_number']
     summary = ST(data_['content'])
-    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
-
-
-def doJob_1():
-    if not os.path.exists('./相关政策/广东省人民政府/政策文件'):
-        os.makedirs('./相关政策/广东省人民政府/政策文件')
+    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': sid,
+    }
+    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
+
+
+# 政策文件
+def doJob_1(sid1):
+    # if not os.path.exists('./相关政策/广东省人民政府/政策文件'):
+    #     os.makedirs('./相关政策/广东省人民政府/政策文件')
     pageSize = getPageSize()
-    data_list = []
+
     num = 1
     url = 'https://search.gd.gov.cn/api/search/file'
     for page in range(1, pageSize + 1):
@@ -182,17 +188,15 @@ def doJob_1():
         data_post = json.dumps(data_post)
         data_json = getDataJson(url, data_post)
         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, sid1)
             num += 1
-    return data_list, num
+    return
 
 
-def doJob_2(num):
+def doJob_2(sid2):
     url = 'https://search.gd.gov.cn/api/search/all'
     types = ['政策解读', '计划规划']
-    data_list = []
+    num = 1
     for type in types:
         data_post = {"label": f"{type}", "position": "all", "keywords": "REITs", "sort": "smart", "site_id": "2",
                      "range": "site", "page": 1, "tag_name": f"{type}", "recommand": 1, "gdbsDivision": "440000",
@@ -200,23 +204,19 @@ def doJob_2(num):
         data_post = json.dumps(data_post)
         data_json = getDataJson(url, data_post)
         for data_ in data_json:
-            data = getData(data_, num)
+            getData(data_, num, sid2)
             time.sleep(1)
-            data_list.append(data)
-            log.info(f'{data[1]}===采集成功')
             num += 1
-    return data_list
+    return
 
 
 def doJob():
-    data_list = []
-    data_list_, num = doJob_1()
-    data_list += data_list_
-    data_list_ = doJob_2(num)
-    data_list += data_list_
-    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/广东省人民政府/广东省人民政府政策文件.xlsx', index=False)
+    sid1 = '1729044231736971266'
+    sid2 = '1729044396395048961'
+    doJob_1(sid1)
+
+    doJob_2(sid2)
+
 
 
 if __name__ == '__main__':