149 lines
6.8 KiB
Python
149 lines
6.8 KiB
Python
# _*_ coding : UTF-8 _*_
|
||
# @Time : 2024/11/11 21:41
|
||
# @UpdateTime : 2024/11/11 21:41
|
||
# @Author : haochen zhong
|
||
# @File : CrawlRenminyoudianbao.py
|
||
# @Software : PyCharm
|
||
# @Comment : 本程序采集人民邮电报
|
||
|
||
|
||
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', '%Y-%m')
|
||
"""中国改革报2017年9月份开始有数据"""
|
||
end_date = datetime.today()
|
||
"""截止到今天"""
|
||
headers = {
|
||
"connection":'keep-alive',
|
||
"host":"rmydb.cnii.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['renminyoudianbao']
|
||
|
||
|
||
async def main():
|
||
collection_names = await db.list_collection_names()
|
||
# 判断数据表是否存在
|
||
if "renminyoudianbao" not in collection_names:
|
||
# 如果不存在，则从2017年9月开始爬取
|
||
print("人民邮电报数据表不存在，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("#ozoom p"):
|
||
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
|
||
start_date = int(start_date.strftime("%Y%m%d"))
|
||
async with AsyncClient(headers=headers, timeout=60) as client:
|
||
response = await client.get("https://rmydb.cnii.com.cn/period/yearMonthDay.json")
|
||
response.encoding = response.charset_encoding
|
||
print(f"一级连接状态：{response.status_code}")
|
||
if response.status_code == 200:
|
||
data = response.json()
|
||
dayList = []
|
||
for value in data.values():
|
||
for item in value.values():
|
||
dayList += item
|
||
dayList.sort()
|
||
dayList = list(filter(lambda x: x >= start_date, list(map(int, dayList))))
|
||
for day in dayList:
|
||
try:
|
||
url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
|
||
print(url)
|
||
response = await client.get(url)
|
||
response.encoding = response.charset_encoding
|
||
print(f"二级连接状态：{response.status_code}")
|
||
if response.status_code == 200:
|
||
data = response.json()
|
||
for item in data:
|
||
banmianming = item["pageName"]
|
||
banmianhao = f"第{item['pageNo']}版"
|
||
for article in item["onePageArticleList"]:
|
||
title = article["mainTitle"]
|
||
url2 = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
|
||
"""https://rmydb.cnii.com.cn/html/2024/20240906/20240906_001/20240906_001_01_523.html"""
|
||
author = article["articleAuthor"]
|
||
if await collection.find_one({"detail_url": url2}, {"_id": False}):
|
||
continue
|
||
print(url2)
|
||
response2 = await client.get(url2)
|
||
response2.encoding = response2.charset_encoding
|
||
print(f"三级连接状态：{response2.status_code}")
|
||
if response2.status_code == 200:
|
||
soup = BeautifulSoup(response2.text, "lxml")
|
||
preTitle = soup.select_one("#PreTitle").text
|
||
title = soup.select_one("#Title").text
|
||
subTitle = soup.select_one("#SubTitle").text
|
||
content = await getContent(soup)
|
||
await collection.insert_one({
|
||
"title": title,
|
||
"subtitle": subTitle,
|
||
"preTitle": preTitle,
|
||
"author": author,
|
||
"banmianming": banmianming,
|
||
"banmianhao": banmianhao,
|
||
'keywordlist': "empty",
|
||
'detail_url': url2,
|
||
'release_time': datetime.strptime(str(day), "%Y%m%d"),
|
||
'insert_timestamp': datetime.today(),
|
||
'content': content
|
||
})
|
||
crawl_num += 1
|
||
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(f"人民邮电报---{day}-----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': datetime.strptime(str(day), "%Y%m%d"),
|
||
'insert_timestamp': datetime.today(),
|
||
'content': 'empty'}
|
||
)
|
||
print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")
|
||
|
||
asyncio.run(main())
|