feat: 添加中国财经报
This commit is contained in:
parent
7d36385331
commit
d82c471644
@ -35,7 +35,7 @@ async def main():
|
||||
# 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("中国民族数据表不存在，开始采集！")
|
||||
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
|
||||
|
||||
144
国内党媒/CrawlZhongguocaijingbao.py
Normal file
144
国内党媒/CrawlZhongguocaijingbao.py
Normal file
@ -0,0 +1,144 @@
|
||||
# _*_ coding : UTF-8 _*_
|
||||
# @Time : 2024/11/18 23:31
|
||||
# @UpdateTime : 2024/11/18 23:31
|
||||
# @Author : haochen zhong
|
||||
# @File : CrawlZhongguocaijingbao.py
|
||||
# @Software : PyCharm
|
||||
# @Comment : 本程序采集中国财经报数据
|
||||
|
||||
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('2017-11', '%Y-%m')
|
||||
"""中国财经报2017年11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['zhongguocaijingbao']
|
||||
|
||||
|
||||
async def main():
|
||||
collection_names = await db.list_collection_names()
|
||||
# 判断数据表是否存在
|
||||
if "zhongguocaijingbao" not in collection_names:
|
||||
# 如果不存在，则从2017年9月开始爬取
|
||||
print("中国财经报数据表不存在，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 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
|
||||
current_date = current_date.replace(day=1)
|
||||
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
|
||||
async with AsyncClient(headers=headers, timeout=60) as client:
|
||||
for month in months:
|
||||
# 构造URL
|
||||
url = "http://114.118.9.73/reader/layout/getSZBDate.do"
|
||||
try:
|
||||
response = await client.post(url, params={"sj": month.strftime("%Y-%m")})
|
||||
response.encoding = response.charset_encoding
|
||||
print(f"一级连接状态：{response.status_code}")
|
||||
if response.status_code == 200:
|
||||
data = response.json()
|
||||
for item in data:
|
||||
url2 = "http://114.118.9.73/reader/layout/findBmMenu.do"
|
||||
response2 = await client.post(url2, params={"docPubTime": item.replace("/", "")})
|
||||
response2.encoding = response2.charset_encoding
|
||||
print(f"二级连接状态：{response2.status_code}")
|
||||
if response2.status_code == 200:
|
||||
data2 = response2.json()
|
||||
for item2 in data2:
|
||||
banmianming = item2["BM"]
|
||||
banmianhao = item2["BC"]
|
||||
url3 = f"http://114.118.9.73/reader/layout/getBmDetail.do?bc={item2['IRCATELOG']}&docpubtime={item.replace('/', '')}"
|
||||
"""http://114.118.9.73/reader/layout/getBmDetail.do?bc=01&docpubtime=20171111"""
|
||||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url3)
|
||||
response3 = await client.get(url3)
|
||||
response3.encoding = response3.charset_encoding
|
||||
print(f"三级连接状态：{response3.status_code}")
|
||||
if response3.status_code == 200:
|
||||
data3 = response3.json()
|
||||
for item3 in data3:
|
||||
url4 = "http://114.118.9.73/reader/layout/detailData.do"
|
||||
response4 = await client.post(url4, params={"guid": item3['ZB_GUID']})
|
||||
response4.encoding = response4.charset_encoding
|
||||
print(f"四级连接状态：{response4.status_code}")
|
||||
if response4.status_code == 200:
|
||||
data4 = response4.json()
|
||||
title = BeautifulSoup(data4['docTitle'], "lxml").text
|
||||
subTitle = BeautifulSoup(data4['fb'], "lxml").text
|
||||
preTitle = BeautifulSoup(data4['yt'], "lxml").text
|
||||
author = data4['docAuthor']
|
||||
content = BeautifulSoup(data4["content"], "lxml").text
|
||||
await collection.insert_one({
|
||||
"title": title,
|
||||
"subtitle": subTitle,
|
||||
"preTitle": preTitle,
|
||||
"author": author,
|
||||
"banmianming": banmianming,
|
||||
"banmianhao": banmianhao,
|
||||
'keywordlist': "empty",
|
||||
'detail_url': f"http://114.118.9.73/epaper/index.html?guid={item3['ZB_GUID']}",
|
||||
'release_time': datetime.strptime(data4["docPubTime"],
|
||||
"%Y/%m/%d %H:%M:%S"),
|
||||
'insert_timestamp': datetime.today(),
|
||||
'content': content
|
||||
})
|
||||
crawl_num += 1
|
||||
print(
|
||||
f"中国财经报---{item}---{banmianming}---{banmianhao}---{title}---采集完成！")
|
||||
await asyncio.sleep(random.randint(5, 15))
|
||||
print(f"中国财经报---{item}---{banmianming}---{banmianhao}-----采集完成！")
|
||||
await asyncio.sleep(random.randint(5, 15))
|
||||
print(f"中国财经报---{item}----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': month,
|
||||
'insert_timestamp': datetime.today(),
|
||||
'content': 'empty'}
|
||||
)
|
||||
|
||||
|
||||
asyncio.run(main())
|
||||
Loading…
x
Reference in New Issue
Block a user