172 lines
8.4 KiB
Python
172 lines
8.4 KiB
Python
|
# _*_ coding : UTF-8 _*_
|
|||
|
|
# @Time : 2024/11/23 03:39
|
|||
|
|
# @UpdateTime : 2024/11/23 03:39
|
|||
|
|
# @Author : haochen zhong
|
|||
|
|
# @File : CrawlZhongguoziranziyuanbao.py
|
|||
|
|
# @Software : PyCharm
|
|||
|
|
# @Comment : 本程序中国自然资源报数据
|
|||
|
|
import asyncio
|
|||
|
|
import random
|
|||
|
|
import uuid
|
|||
|
|
from datetime import datetime
|
|||
|
|
|
|||
|
|
from httpx import AsyncClient
|
|||
|
|
from motor.motor_asyncio import AsyncIOMotorClient
|
|||
|
|
|
|||
|
|
start_date = datetime.strptime('2018-05-18', '%Y-%m-%d')
|
|||
|
|
"""中国自然资源报2018年5月18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['zhongguoziranziyuanbao']
|
|||
|
|
|
|||
|
|
|
|||
|
|
async def main():
|
|||
|
|
collection_names = await db.list_collection_names()
|
|||
|
|
# 判断数据表是否存在
|
|||
|
|
if "zhongguoziranziyuanbao" not in collection_names:
|
|||
|
|
# 如果不存在，则从2017年9月开始爬取
|
|||
|
|
print("中国自然资源报数据表不存在，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 heartbeat():
|
|||
|
|
"""
|
|||
|
|
心跳检测
|
|||
|
|
:return:
|
|||
|
|
"""
|
|||
|
|
uid = uuid.uuid4().__str__()
|
|||
|
|
"""随机UUID"""
|
|||
|
|
async with AsyncClient(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',
|
|||
|
|
"myidentity": uid}) as client:
|
|||
|
|
response = await client.get(url="http://szb.iziran.net//user/ipLogin")
|
|||
|
|
if response.status_code == 200:
|
|||
|
|
global headers
|
|||
|
|
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',
|
|||
|
|
"myidentity": uid,
|
|||
|
|
"Site": 'iziran',
|
|||
|
|
"Host": "szb.iziran.net"
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
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
|
|||
|
|
heart_num = 0
|
|||
|
|
date_url = "http://szb.iziran.net//xcms-pc/static/cache/bz1.json"
|
|||
|
|
async with AsyncClient(headers=headers, timeout=60) as client:
|
|||
|
|
response = await client.get(date_url)
|
|||
|
|
response.encoding = response.charset_encoding
|
|||
|
|
if response.status_code == 200:
|
|||
|
|
dateList = response.json()
|
|||
|
|
dateList = list(
|
|||
|
|
filter(lambda x: x >= start_date, list(map(lambda x: datetime.strptime(x, '%Y-%m-%d'), dateList))))
|
|||
|
|
dateList = dateList[::-1]
|
|||
|
|
await heartbeat()
|
|||
|
|
client.headers = headers
|
|||
|
|
for date in dateList:
|
|||
|
|
try:
|
|||
|
|
if heart_num > 63:
|
|||
|
|
await heartbeat()
|
|||
|
|
client.headers = headers
|
|||
|
|
heart_num = 0
|
|||
|
|
url = "http://szb.iziran.net//bz/queryPageByDate"
|
|||
|
|
params = {
|
|||
|
|
"date": date.strftime("%Y-%m-%d"),
|
|||
|
|
"columnId": 1
|
|||
|
|
}
|
|||
|
|
response = await client.post(url, params=params)
|
|||
|
|
heart_num += 1
|
|||
|
|
response.encoding = response.charset_encoding
|
|||
|
|
print(f"一级连接状态：{response.status_code}")
|
|||
|
|
if response.status_code == 200:
|
|||
|
|
data = response.json().get("data", {"pages": []}).get("pages", [])
|
|||
|
|
for item in data:
|
|||
|
|
if heart_num > 63:
|
|||
|
|
await heartbeat()
|
|||
|
|
client.headers = headers
|
|||
|
|
heart_num = 0
|
|||
|
|
banmianming = item["name"]
|
|||
|
|
banmianhao = item["number"]
|
|||
|
|
url1 = f"http://szb.iziran.net//bz/queryArticleByPage"
|
|||
|
|
params = {"pageId": item["id"]}
|
|||
|
|
response2 = await client.post(url1, params=params)
|
|||
|
|
heart_num += 1
|
|||
|
|
response2.encoding = response2.charset_encoding
|
|||
|
|
print(f"二级连接状态：{response2.status_code}")
|
|||
|
|
if response2.status_code == 200:
|
|||
|
|
data2 = response2.json().get("data", {"articles": []}).get("articles", [])
|
|||
|
|
for item2 in data2:
|
|||
|
|
url2 = f"http://szb.iziran.net/bz/html/content.html?date={date.strftime('%Y-%m-%d')}&pageIndex={item['index']}&cid=1&articleId={item2['id']}&articleIndex={item2['index']}&pageId={item2['pageId']}"
|
|||
|
|
if await collection.find_one({"detail_url": url2}, {"_id": False}):
|
|||
|
|
continue
|
|||
|
|
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
|
|||
|
|
url3 = "http://szb.iziran.net//bz/getArticleById"
|
|||
|
|
params = {"articleId": item2["id"]}
|
|||
|
|
response3 = await client.post(url3, params=params)
|
|||
|
|
heart_num += 1
|
|||
|
|
response3.encoding = response3.charset_encoding
|
|||
|
|
print(f"三级连接状态：{response3.status_code}")
|
|||
|
|
if response3.status_code == 200:
|
|||
|
|
data3 = response3.json().get("data", {})
|
|||
|
|
await collection.insert_one({
|
|||
|
|
"title": data3.get("title", ""),
|
|||
|
|
"subtitle": data3.get("subtitle", ""),
|
|||
|
|
"preTitle": data3.get("introTitle", ""),
|
|||
|
|
"author": data3.get("author", ""),
|
|||
|
|
"banmianming": banmianming,
|
|||
|
|
"banmianhao": banmianhao,
|
|||
|
|
'keywordlist': "empty",
|
|||
|
|
'detail_url': url2,
|
|||
|
|
'release_time': date,
|
|||
|
|
'insert_timestamp': datetime.today(),
|
|||
|
|
'content': data3.get("text", "")
|
|||
|
|
})
|
|||
|
|
crawl_num += 1
|
|||
|
|
print(
|
|||
|
|
f"中国自然资源报---{date.strftime('%Y-%m-%d')}---{banmianming}---{banmianhao}---{data3.get('title', '')}---采集完成！")
|
|||
|
|
await asyncio.sleep(random.randint(5, 15))
|
|||
|
|
print(
|
|||
|
|
f"中国自然资源报---{date.strftime('%Y-%m-%d')}---{banmianming}---{banmianhao}-----采集完成！")
|
|||
|
|
await asyncio.sleep(random.randint(5, 15))
|
|||
|
|
print(
|
|||
|
|
f"中国自然资源报---{date.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': date,
|
|||
|
|
'insert_timestamp': datetime.today(),
|
|||
|
|
'content': 'empty'}
|
|||
|
|
)
|
|||
|
|
print(f"中国自然资源报采集完毕，共采集{crawl_num}条数据！")
|
|||
|
|
|
|||
|
|
|
|||
|
|
asyncio.run(main())
|