# _*_ coding : UTF-8 _*_
# @Time : 2024/11/13 03:55
# @UpdateTime : 2024/11/13 03:55
# @Author : haochen zhong
# @File : CrawlFazhiribao.py
# @Software : PyCharm
# @Comment : 本程序采集法治日报数据
import asyncio
import random
import re
from datetime import datetime, timedelta
from bs4 import BeautifulSoup
from httpx import AsyncClient
from motor.motor_asyncio import AsyncIOMotorClient
start_date = datetime.strptime('2021-01-01', '%Y-%m-%d')
"""法治日报2021年1月1日开始有数据"""
end_date = datetime.today()
"""截止到今天"""
headers = {
# "connection": 'keep-alive',
# "host": "epaper.legaldaily.com.cn",
'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['buweijiguanbao']
collection = db['fazhiribao']
async def main():
collection_names = await db.list_collection_names()
# 判断数据表是否存在
if "fazhiribao" not in collection_names:
# 如果不存在，则从2017年9月开始爬取
print("法治日报数据表不存在，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("#contenttext "):
para = p.text.strip()
if para:
content += para
content += '\n'
return content
async def getData(start_date: datetime, end_date: datetime):
"""
:param start_date: 开始日期
:param end_date: 结束日期
:return: None
"""
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 = f"http://epaper.legaldaily.com.cn/fzrb/content/{date_now_s}/"
url = base_url + "Page01TB.htm"
"""http://epaper.legaldaily.com.cn/fzrb/content/20210101/Page01TB.htm"""
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
try:
async with AsyncClient(headers=headers, timeout=60) as client:
response = await client.get(url=url)
response.encoding = response.charset_encoding
print(f"一级连接状态：{response.status_code}")
if response.status_code == 200:
pattern = r'(\d+):([^<]+)'
for item in re.findall(pattern, response.text, re.IGNORECASE):
banmianhao = item[1]
banmianming = item[-1]
url1 = base_url + item[0]
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1)
response1 = await client.get(url=url1)
response1.encoding = response1.charset_encoding
print(f"二级连接状态：{response1.status_code}")
if response1.status_code == 200:
soup1 = BeautifulSoup(response1.text, "lxml")
for item2 in soup1.select(".overlink"):
title = item2.get("onmousemove", "").replace(";", "").replace("'","").split("=")[-1].strip()
url2 = base_url + item2.get("href")
if await collection.find_one({"detail_url": url2}, {"_id": False}):
continue
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
response2 = await client.get(url=url2)
response2.encoding = response2.charset_encoding
print(f"三级连接状态：{response2.status_code}")
if response2.status_code == 200:
soup2 = BeautifulSoup(response2.text, "lxml")
try:
pattern = r'\s*]*>\s*]*>\s*]*>([^<]+)'
match= re.search(pattern, response2.text, re.IGNORECASE)
if match:
preTitle=match.group(1).strip()
else:
preTitle = ""
except:
preTitle = ""
try:
pattern = r'\s*]*>\s*]*>\s*]*>]*>([^<]+)'
match = re.search(pattern, response2.text, re.IGNORECASE)
if match:
title = match.group(1).strip()
else:
title = title
except:
title = ""
try:
pattern = r'\s*]*>\s*]*>\s*]*>([^<]+)'
match = re.search(pattern, response2.text, re.IGNORECASE)
if match:
subtitle= match.group(1).strip()
else:
subtitle = ""
except:
subtitle = ""
try:
pattern = r'\s*]*>\s*]*>\s*(.*?)\s*'
match = re.search(pattern, response2.text, re.IGNORECASE)
if match:
author = match.group(1).strip()
else:
author = ""
except:
author = ""
content= await getContent(soup2)
await collection.insert_one({
"title": title,
"subtitle": subtitle,
"preTitle": preTitle,
"author": 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"法治日报---{date_now_s}---{banmianming}---{banmianhao}---{title}---采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"法治日报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"法治日报---{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"法治日报采集完毕，共采集{crawl_num}条数据！")
asyncio.run(main())