200 lines
11 KiB
Python
200 lines
11 KiB
Python
|
# _*_ coding : UTF-8 _*_
|
|||
|
|
# @Time : 2024/11/10 21:23
|
|||
|
|
# @UpdateTime : 2024/11/10 21:23
|
|||
|
|
# @Author : haochen zhong
|
|||
|
|
# @File : CrawlKejiribao.py
|
|||
|
|
# @Software : PyCharm
|
|||
|
|
# @Comment : 本程序采集科技日报数据
|
|||
|
|
|
|||
|
|
|
|||
|
|
import asyncio
|
|||
|
|
import random
|
|||
|
|
from datetime import datetime
|
|||
|
|
|
|||
|
|
from bs4 import BeautifulSoup
|
|||
|
|
from httpx import AsyncClient
|
|||
|
|
from motor.motor_asyncio import AsyncIOMotorClient
|
|||
|
|
|
|||
|
|
start_date = datetime.strptime('2011-01', '%Y-%m')
|
|||
|
|
"""科技日报报2011年1月份开始有数据"""
|
|||
|
|
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['kejiribao']
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def main():
|
|||
|
|
collection_names = await db.list_collection_names()
|
|||
|
|
# 判断数据表是否存在
|
|||
|
|
if "kejiribao" not in collection_names:
|
|||
|
|
# 如果不存在，则从2017年9月开始爬取
|
|||
|
|
print("科技日报数据表不存在，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("#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
|
|||
|
|
# 创建一个列表保存月份
|
|||
|
|
months = []
|
|||
|
|
# 从开始日期到结束日期，每个月份都添加到列表中
|
|||
|
|
current_date = start_date
|
|||
|
|
while current_date <= end_date:
|
|||
|
|
months.append(current_date)
|
|||
|
|
# 增加一个月
|
|||
|
|
if current_date.month == 12:
|
|||
|
|
current_date = current_date.replace(year=current_date.year + 1, month=1)
|
|||
|
|
else:
|
|||
|
|
current_date = current_date.replace(month=current_date.month + 1)
|
|||
|
|
# 遍历月份列表
|
|||
|
|
for month in months:
|
|||
|
|
# 构造URL
|
|||
|
|
url = f'https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{month.strftime("%Y-%m")}/period.xml'
|
|||
|
|
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2011-10/period.xml"""
|
|||
|
|
print(url)
|
|||
|
|
async with AsyncClient(headers=headers, timeout=60) as client:
|
|||
|
|
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, 'xml')
|
|||
|
|
for period in soup.select("period"):
|
|||
|
|
period_name = datetime.strptime(period.select_one("period_name").text.strip(), "%Y-%m-%d")
|
|||
|
|
front_page = period.select_one("front_page").text.strip()
|
|||
|
|
try:
|
|||
|
|
url1 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
|
|||
|
|
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/node_2.htm"""
|
|||
|
|
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 item in soup2.select("#pageLink"):
|
|||
|
|
banmianming = item.text.split("：")[-1]
|
|||
|
|
banmianhao = item.text.split("：")[0]
|
|||
|
|
url2 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
|
|||
|
|
"href").replace("./", "").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')
|
|||
|
|
pages = soup3.select(".ul02_l a")
|
|||
|
|
if pages:
|
|||
|
|
titleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > strong"
|
|||
|
|
subTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(5)"
|
|||
|
|
preTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(1)"
|
|||
|
|
authorTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(7)"
|
|||
|
|
else:
|
|||
|
|
pages = soup3.select(".title a")
|
|||
|
|
titleTag = ".biaoti"
|
|||
|
|
subTitleTag = ".futi"
|
|||
|
|
preTitleTag = ".yinti"
|
|||
|
|
authorTag = ".autor"
|
|||
|
|
for item2 in pages:
|
|||
|
|
url3 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
|
|||
|
|
"href")
|
|||
|
|
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/content_579753.htm?div=-1"""
|
|||
|
|
if await collection.find_one({"detail_url": url3}, {"_id": False}):
|
|||
|
|
continue
|
|||
|
|
title = item2.text.strip()
|
|||
|
|
print(url3)
|
|||
|
|
response4 = await client.get(url3)
|
|||
|
|
response4.encoding = response4.charset_encoding
|
|||
|
|
print(f"四级连接状态：{response4.status_code}")
|
|||
|
|
if response4.status_code == 200:
|
|||
|
|
soup4 = BeautifulSoup(response4.text, 'lxml')
|
|||
|
|
try:
|
|||
|
|
title = soup4.select_one(titleTag).text.strip()
|
|||
|
|
except:
|
|||
|
|
title = title
|
|||
|
|
try:
|
|||
|
|
subTitle = soup4.select(subTitleTag)[0].text.strip()
|
|||
|
|
except:
|
|||
|
|
subTitle = ""
|
|||
|
|
try:
|
|||
|
|
author = soup4.select_one(authorTag).text.strip()
|
|||
|
|
except:
|
|||
|
|
author = ""
|
|||
|
|
try:
|
|||
|
|
perTitle = soup4.select(preTitleTag)[-1].text.strip()
|
|||
|
|
except:
|
|||
|
|
perTitle = ""
|
|||
|
|
try:
|
|||
|
|
keywordlist = soup4.find("founder-keyword").text.strip()
|
|||
|
|
except:
|
|||
|
|
keywordlist = ""
|
|||
|
|
content = await getContent(soup4)
|
|||
|
|
await collection.insert_one({
|
|||
|
|
"title": title,
|
|||
|
|
"subtitle": subTitle,
|
|||
|
|
"preTitle": perTitle,
|
|||
|
|
"author": author,
|
|||
|
|
"banmianming": banmianming,
|
|||
|
|
"banmianhao": banmianhao,
|
|||
|
|
'keywordlist': keywordlist,
|
|||
|
|
'detail_url': url3,
|
|||
|
|
'release_time': period_name,
|
|||
|
|
'insert_timestamp': datetime.today(),
|
|||
|
|
'content': content
|
|||
|
|
})
|
|||
|
|
crawl_num += 1
|
|||
|
|
print(
|
|||
|
|
f"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
|
|||
|
|
await asyncio.sleep(random.randint(5, 15))
|
|||
|
|
print(
|
|||
|
|
f"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
|
|||
|
|
await asyncio.sleep(random.randint(5, 15))
|
|||
|
|
print(f"科技日报---{period_name.strftime('%Y-%m-%d')}-----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': period_name,
|
|||
|
|
'insert_timestamp': datetime.today(),
|
|||
|
|
'content': 'empty'}
|
|||
|
|
)
|
|||
|
|
print(f"科技日报采集完毕，共采集{crawl_num}条数据！")
|
|||
|
|
|
|||
|
|
|
|||
|
|
asyncio.run(main())
|