182 lines
8.8 KiB
Python
182 lines
8.8 KiB
Python
# _*_ 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'<a class="atitle" href="([^"]+)">(\d+):([^<]+)</a>'
|
||
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'<!--引题-->\s*<tr[^>]*>\s*<td[^>]*>\s*<span[^>]*>([^<]+)</span>'
|
||
match= re.search(pattern, response2.text, re.IGNORECASE)
|
||
if match:
|
||
preTitle=match.group(1).strip()
|
||
else:
|
||
preTitle = ""
|
||
except:
|
||
preTitle = ""
|
||
try:
|
||
pattern = r'<!--标题-->\s*<tr[^>]*>\s*<td[^>]*>\s*<span[^>]*><strong[^>]*>([^<]+)</span>'
|
||
match = re.search(pattern, response2.text, re.IGNORECASE)
|
||
if match:
|
||
title = match.group(1).strip()
|
||
else:
|
||
title = title
|
||
except:
|
||
title = ""
|
||
try:
|
||
pattern = r'<!--肩题-->\s*<tr[^>]*>\s*<td[^>]*>\s*<span[^>]*>([^<]+)</span>'
|
||
match = re.search(pattern, response2.text, re.IGNORECASE)
|
||
if match:
|
||
subtitle= match.group(1).strip()
|
||
else:
|
||
subtitle = ""
|
||
except:
|
||
subtitle = ""
|
||
try:
|
||
pattern = r'<!--作者-->\s*<tr[^>]*>\s*<td[^>]*>\s*(.*?)\s*</td>'
|
||
|
||
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())
|