feat: 添加安徽日报同步版本
This commit is contained in:
parent
41053ada17
commit
547baec801
143
地方政策/报刊/CrawlAnhui-sync.py
Normal file
143
地方政策/报刊/CrawlAnhui-sync.py
Normal file
@ -0,0 +1,143 @@
|
||||
# _*_ coding : UTF-8 _*_
|
||||
# @Time : 2024/11/13 13:42
|
||||
# @UpdateTime : 2024/11/13 13:42
|
||||
# @Author : haochen zhong
|
||||
# @File : CrawlAnhui-sync.py
|
||||
# @Software : PyCharm
|
||||
# @Comment : 本程序采集
|
||||
|
||||
import random
|
||||
import time
|
||||
from datetime import timedelta, datetime
|
||||
|
||||
import pymongo
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
start_date = datetime.strptime('2017-09-29', '%Y-%m-%d')
|
||||
"""安徽日报报2018年09月29日开始有数据"""
|
||||
end_date = datetime.today()
|
||||
"""截止到今天"""
|
||||
headers = {
|
||||
'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.42'}
|
||||
|
||||
# 链接数据库
|
||||
client = pymongo.MongoClient('mongodb://localhost:27017')
|
||||
db = client['dfdm_sjribao']
|
||||
collection = db['anhuiribao']
|
||||
|
||||
|
||||
def main():
|
||||
collection_names = db.list_collection_names()
|
||||
# 判断数据表是否存在
|
||||
if "anhuiribao" not in collection_names:
|
||||
# 如果不存在，则从2017年9月开始爬取
|
||||
print("安徽日报报数据表不存在，开始采集！")
|
||||
getData(start_date, end_date)
|
||||
else:
|
||||
# 如果存在，则从数据库中获取最后一条记录的日期
|
||||
last_record = collection.find_one(sort=[('release_time', -1)])
|
||||
last_date_str = last_record['release_time']
|
||||
print("数据库截止时间:", last_date_str)
|
||||
getData(last_date_str, end_date)
|
||||
|
||||
|
||||
def getContent(soup: BeautifulSoup) -> str:
|
||||
"""
|
||||
:param soup: BeautifulSoup对象
|
||||
:return: 文章内容
|
||||
"""
|
||||
content = ""
|
||||
for p in soup.select(".content p"):
|
||||
para = p.text.strip()
|
||||
if para:
|
||||
content += para
|
||||
content += '\n'
|
||||
return content
|
||||
|
||||
|
||||
def getData(start_date: datetime, end_date: datetime):
|
||||
crawl_num = 0
|
||||
for i in range((end_date - start_date).days):
|
||||
date_now = start_date + timedelta(days=i)
|
||||
date_now_s = date_now.strftime('%Y%m/%d')
|
||||
base_url = "https://szb.ahnews.com.cn/ahrb/layout/" + date_now_s + '/'
|
||||
url = base_url + 'node_01.html'
|
||||
"""https://szb.ahnews.com.cn/ahrb/layout/201811/01/node_01.html"""
|
||||
try:
|
||||
print(url)
|
||||
response = requests.get(url=url, headers=headers, timeout=60)
|
||||
response.encoding = response.apparent_encoding
|
||||
print(f"一级连接状态：{response.status_code}")
|
||||
if response.status_code == 200:
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
for item in soup.select(".Chunkiconlist p > a:nth-child(1)"):
|
||||
banmianming = item.text.split("：")[-1].strip()
|
||||
banmianhao = item.text.split("：")[0].replace(" ", "").replace(" ", "").strip()
|
||||
url1 = base_url + item.get("href")
|
||||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1)
|
||||
response2 = requests.get(url1, headers=headers, timeout=60)
|
||||
response2.encoding = response2.apparent_encoding
|
||||
print(f"二级连接状态：{response2.status_code}")
|
||||
if response2.status_code == 200:
|
||||
soup2 = BeautifulSoup(response2.text, 'lxml')
|
||||
for item2 in soup2.select(".newslist a"):
|
||||
url2 = "https://szb.ahnews.com.cn/ahrb/" + item2.get("href")[9:]
|
||||
"""https://szb.ahnews.com.cn/ahrb/content/201709/29/c17310.html"""
|
||||
if collection.find_one({"detail_url": url2}, {"_id": False}):
|
||||
continue
|
||||
title = item2.text.strip()
|
||||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
|
||||
response3 = requests.get(url=url2, headers=headers, timeout=60)
|
||||
response3.encoding = response3.apparent_encoding
|
||||
print(f"三级连接状态：{response3.status_code}")
|
||||
if response3.status_code == 200:
|
||||
soup3 = BeautifulSoup(response3.text, 'lxml')
|
||||
content = getContent(soup3)
|
||||
try:
|
||||
title = soup3.select(".newsdetatit h3")[0].text.strip()
|
||||
except:
|
||||
title = title
|
||||
try:
|
||||
subTitle = soup3.select(".newsdetatext p")[0].text.strip()
|
||||
except:
|
||||
subTitle = ""
|
||||
collection.insert_one({
|
||||
"title": title,
|
||||
"subtitle": subTitle,
|
||||
"preTitle": "",
|
||||
"author": "",
|
||||
"banmianming": banmianming,
|
||||
"banmianhao": banmianhao,
|
||||
'keywordlist': 'empty',
|
||||
'detail_url': url2,
|
||||
'release_time': date_now,
|
||||
'insert_timestamp': datetime.today(),
|
||||
'content': content
|
||||
})
|
||||
crawl_num += 1
|
||||
print(f"安徽日报---{date_now_s}---{banmianming}---{banmianhao}---{title}---采集完成！")
|
||||
time.sleep(random.randint(5, 15))
|
||||
print(f"安徽日报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
|
||||
time.sleep(random.randint(5, 15))
|
||||
print(f"安徽日报---{date_now_s}-----采集完成！")
|
||||
time.sleep(random.randint(5, 15))
|
||||
except Exception as e:
|
||||
print(e)
|
||||
collection.insert_one(
|
||||
{'banmianhao': 'empty',
|
||||
'banmianming': 'empty',
|
||||
'preTitle': 'empty',
|
||||
'title': 'empty',
|
||||
'subtitle': 'empty',
|
||||
'author': 'empty',
|
||||
'keywordlist': 'empty',
|
||||
'detail_url': url,
|
||||
'release_time': date_now,
|
||||
'insert_timestamp': datetime.today(),
|
||||
'content': 'empty'}
|
||||
)
|
||||
print(f"安徽日报采集完毕，共采集{crawl_num}条数据！")
|
||||
|
||||
|
||||
main()
|
||||
Loading…
x
Reference in New Issue
Block a user