提交 5bba0870 作者: 薛凌堃

江西省人民政府

上级 07bd3604
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 = '江西省人民政府'
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',
......@@ -54,15 +64,14 @@ def getDataJson():
def getContent(url, num, publishDate):
fjhref_list = ''
fjtitle_list = ''
id_list = []
soup = getSoup(url)
contentWithTag = soup.find('div', attrs={'id': 'zoom'})
img_list = contentWithTag.find_all('img')
num_ = 1
for img in img_list:
fj_href = 'http://www.jiangxi.gov.cn' + img.get('src')
fjhref_list += fj_href + '\n'
fj_title = img.get('title')
if fj_title == '':
fj_title = str(num_)
......@@ -70,13 +79,11 @@ def getContent(url, num, publishDate):
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/江西省人民政府/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)
img['href'] = full_path
try:
scripts = contentWithTag.find_all('script')
for script in scripts:
......@@ -90,12 +97,11 @@ def getContent(url, num, publishDate):
except:
pass
content = contentWithTag.text.lstrip().strip()
return content, fjtitle_list, fjhref_list
return content, contentWithTag, id_list
def doJob():
if not os.path.exists('./相关政策/江西省人民政府/政策文件'):
os.makedirs('./相关政策/江西省人民政府/政策文件')
data_json = getDataJson()
data_list = []
num = 1
......@@ -111,18 +117,43 @@ def doJob():
-1].text.lstrip().strip()
summary = soup.find('table', class_='jcse-service-table').find_all('tr')[2].text.lstrip().strip()
href = soup.find('table', class_='jcse-service-table').find_all('tr')[3].find('a').get('href')
# 根据链接判重
is_member = baseCore.r.sismember('REITs::' + webname, href)
if is_member:
continue
publishDate = writtenDate
origin = '江西省人民政府'
content, fjtitle_list, fjhref_list = getContent(href, num, publishDate)
data = [num, title, publishDate, origin, href, writtenDate, organ, pub_hao, summary, content, fjtitle_list,
fjhref_list]
data_list.append(data)
log.info(f'{title}===采集成功')
content, contentWithTag, id_list = getContent(href, num, publishDate)
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/江西省人民政府/江西省人民政府政策文件.xlsx', index=False)
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': '1729043445107838978',
}
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)
if __name__ == '__main__':
doJob()
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论