166 lines
8.1 KiB
Python
166 lines
8.1 KiB
Python
# _*_ coding : UTF-8 _*_
|
||
# @Time : 2024/11/13 02:34
|
||
# @UpdateTime : 2024/11/13 02:34
|
||
# @Author : haochen zhong
|
||
# @File : CrawlRenmingonganbao.py
|
||
# @Software : PyCharm
|
||
# @Comment : 本程序采集人民公安报数据
|
||
|
||
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
|
||
|
||
pattern = r"window\.location\.href=['\"](.*?)['\"]"
|
||
"""正则匹配ID"""
|
||
start_date = datetime.strptime('2020-04-01', '%Y-%m-%d')
|
||
"""人民公安报2020年4月1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['buweijiguanbao']
|
||
collection = db['renmingonganbao']
|
||
|
||
|
||
async def main():
|
||
collection_names = await db.list_collection_names()
|
||
# 判断数据表是否存在
|
||
if "renmingonganbao" not in collection_names:
|
||
# 如果不存在，则从2017年9月开始爬取
|
||
print("人民公安报数据表不存在，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("div.content_main > div:nth-child(2) .contentP"):
|
||
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 + 1)
|
||
date_now_s = date_now.strftime('%Y_%m_%d')
|
||
url = f"http://epaper.cpd.com.cn/szb/wwwcpd_9/dzb_16465/rmga/{date_now.year}/{date_now_s}/"
|
||
"""http://epaper.cpd.com.cn/szb/wwwcpd_9/dzb_16465/rmga/2020/2020_04_05/"""
|
||
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)
|
||
response.encoding = response.charset_encoding
|
||
text = response.text
|
||
match = re.search(pattern, text)
|
||
if match:
|
||
url = url + match.group(1).replace("./", "")
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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')
|
||
cont_main = soup.select_one(".tab-title")
|
||
if cont_main:
|
||
script_tag = cont_main.find("script")
|
||
if script_tag:
|
||
script_content = script_tag.string
|
||
soup1 = BeautifulSoup(
|
||
script_content.replace("document.write('", "").replace("')", "").replace(";",
|
||
"").replace(
|
||
"'+'", "").strip(), "lxml")
|
||
for item in soup1.select(".title-item"):
|
||
banmianming = item.select_one(".title").text.split(" ")[-1]
|
||
banmianhao = item.select_one(".title").text.split(" ")[0]
|
||
for item2 in item.select(".title-list a"):
|
||
title = item2.text
|
||
url2 = item2.get("href")
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
|
||
response2 = await client.get(url2)
|
||
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')
|
||
try:
|
||
title = soup2.select_one(
|
||
".cont-box > div>div:nth-child(2)").text.strip()
|
||
except:
|
||
title = title
|
||
try:
|
||
subtitle = soup2.select_one(
|
||
".cont-box > div>div:nth-child(3)").text.strip()
|
||
except:
|
||
subtitle = ""
|
||
try:
|
||
preTitle = soup2.select_one(
|
||
".cont-box > div>div:nth-child(1)").text.strip()
|
||
except:
|
||
preTitle = ""
|
||
content = await getContent(soup2)
|
||
await collection.insert_one({
|
||
"title": title,
|
||
"subtitle": subtitle,
|
||
"preTitle": 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"人民公安报---{date_now_s}---{banmianming}---{banmianhao}---{title}---采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"人民公安报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"人民公安报---{date_now_s}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
except Exception as 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(e)
|
||
print(f"人民公安报采集完毕，共采集{crawl_num}条数据！")
|
||
|
||
|
||
asyncio.run(main())
|