146 lines
6.7 KiB
Python
146 lines
6.7 KiB
Python
# _*_ coding : UTF-8 _*_
|
||
# @Time : 2024/11/08 20:29
|
||
# @UpdateTime : 2024/11/08 20:29
|
||
# @Author : haochen zhong
|
||
# @File : CrawlAnhui.py
|
||
# @Software : PyCharm
|
||
# @Comment : 本程序采集安徽日报数字报数据
|
||
|
||
|
||
import asyncio
|
||
import random
|
||
from datetime import datetime, timedelta
|
||
|
||
from bs4 import BeautifulSoup
|
||
from httpx import AsyncClient
|
||
from motor.motor_asyncio import AsyncIOMotorClient
|
||
|
||
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 = AsyncIOMotorClient('mongodb://localhost:27017')
|
||
db = client['dfdm_sjribao']
|
||
collection = db['anhuiribao']
|
||
|
||
|
||
async def main():
|
||
collection_names = await 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！")
|
||
await 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 = await 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)
|
||
await getData(last_date_str, end_date)
|
||
|
||
|
||
async 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
|
||
|
||
|
||
async 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 + 1)
|
||
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:
|
||
async with AsyncClient(headers=headers, timeout=60) as client:
|
||
print(url)
|
||
response = await client.get(url)
|
||
response.encoding = response.charset_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(url1)
|
||
response2= await client.get(url1)
|
||
response2.encoding = response2.charset_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 await collection.find_one({"detail_url": url2}, {"_id": False}):
|
||
continue
|
||
title = item2.text.strip()
|
||
print(url2)
|
||
response3 = await client.get(url2)
|
||
response3.encoding = response3.charset_encoding
|
||
print(f"三级连接状态：{response3.status_code}")
|
||
if response3.status_code == 200:
|
||
soup3 = BeautifulSoup(response3.text, 'lxml')
|
||
content = await 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 = ""
|
||
await 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！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"安徽日报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"安徽日报---{date_now_s}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
except Exception as e:
|
||
print(e)
|
||
await 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！")
|
||
|
||
asyncio.run(main())
|
||
|