湖北省人民政府

REITs专题数据/policy-hubei.py

-import os
+import os
@@ -8,16 +8,21 @@ from bs4 import BeautifulSoup
 from selenium.webdriver.common.by import By
 from selenium.webdriver.firefox.options import Options
 from selenium.webdriver.firefox.service import Service
-
-from base import BaseCore
 import time
 from selenium.webdriver import Firefox
 from selenium import webdriver
 
-
+import BaseCore
 
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
+
+from reits import Policy
+policy = Policy()
+
+
+topic = 'policy'
+webname = '湖北省人民政府'
 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',
 }
@@ -62,73 +67,96 @@ def getDataJson(page):
 
 def getContent(driver, url, num):
     driver.get(url)
+
     time.sleep(5)
-    fjhref_list = ''
-    fjtitle_list = ''
-    publishDate = driver.find_element(By.CLASS_NAME,'hbgov-article-meta-time').text.split('发布时间：')[1].lstrip().strip()
-    contentWithTag = driver.find_element(By.CLASS_NAME,'hbgov-article-content')
-    img_list = contentWithTag.find_elements(By.TAG_NAME,'img')
+    id_list = []
+    page_source = driver.page_source
+    soup = BeautifulSoup(page_source, 'html.parser')
+    policy.paserUrl(soup, url)
+    publishDate = soup.find(class_='hbgov-article-meta-time').text.split('发布时间：')[1].lstrip().strip()[:10]
+    time.sleep(2)
+    contentWithTag = soup.find(class_='hbgov-article-content')
+
+    img_list = contentWithTag.find_all(class_='img')
     num_ = 1
     for img in img_list:
         fj_title = img.get_attribute('title')
         fj_href = img.get_attribute('src')
-        fjhref_list += fj_href + '\n'
+
         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[:10]}-{fj_title}'
-        fjtitle_list += fj_title + '\n'
-        fjcontent = getFjContent(fj_href)
-        file = f'./相关政策/湖北省人民政府/政策文件/{fj_title}'
-        if os.path.exists(file):
-            fj_title = fj_title.replace(category,f'-{num_}') + category
-            num_ += 1
-        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)
+            img['href'] = full_path
     content = contentWithTag.text.lstrip().strip()
-    fjtitle_list = fjtitle_list.lstrip().strip()
-    fjhref_list = fjhref_list.lstrip().strip()
-    return publishDate, content, fjtitle_list, fjhref_list
+
+    return publishDate, content, contentWithTag, id_list
 
 
 def getData(driver, data_, num):
     title = data_['DOCTITLE']
     origin = data_['SITENAME']
     pub_hao = data_['fileNum']
-    writtenDate = data_['PUBDATE']
+    writtenDate = str(data_['PUBDATE'])[:10]
     organ = data_['publisher']
     summary = data_['highlight']['DOCCONTENT'][0]
     href = data_['DOCPUBURL']
-    publishDate, content, fjtitle_list, fjhref_list = getContent(driver, href, num)
-    data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
-            fjhref_list]
-    return data
+    # 根据链接判重
+    is_member = baseCore.r.sismember('REITs::' + webname, href)
+    if is_member:
+        return
+    publishDate, content, contentWithTag, id_list = getContent(driver, href, 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.replace('</em>', '').replace('<em>', ''),
+        'createDate': time_now,
+        'sid': '1729044085724860418',
+    }
+    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():
-    service = Service(r'F:\spider\firefox\geckodriver.exe')
+    service = Service(r'D:/soft/geckodriver.exe')
     options = Options()
     options.set_preference("general.useragent.override", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3")
     driver = webdriver.Firefox(options=options, service=service)
-    if not os.path.exists('./相关政策/湖北省人民政府/政策文件'):
-        os.makedirs('./相关政策/湖北省人民政府/政策文件')
-    data_list = []
+
     num = 1
     for page in range(1, 3):
         data_json = getDataJson(page)
         for data_ in data_json:
             data = getData(driver, data_, num)
-            data_list.append(data)
-            log.info(f'{data[1]}===采集成功')
+
             num += 1
     driver.close()
-    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/湖北省人民政府/湖北省人民政府政策文件.xlsx', index=False)
 
 #
 if __name__ == '__main__':