299 lines
18 KiB
Python
299 lines
18 KiB
Python
# _*_ coding : UTF-8 _*_
|
||
# @Time : 2025/02/07 22:33
|
||
# @UpdateTime : 2025/02/07 22:33
|
||
# @Author : sonder
|
||
# @File : CrawlZhongguoqingnianbao.py
|
||
# @Software : PyCharm
|
||
# @Comment : 本程序
|
||
|
||
import asyncio
|
||
import random
|
||
from datetime import datetime
|
||
|
||
from bs4 import BeautifulSoup, Comment
|
||
from httpx import AsyncClient
|
||
from motor.motor_asyncio import AsyncIOMotorClient
|
||
|
||
start_date = datetime.strptime('2011-01', '%Y-%m')
|
||
"""中国青年报2011-01开始有效数据"""
|
||
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'}
|
||
|
||
pattern = r'<a href=([^>]+)><div[^>]*>([^<]+)</div></a>'
|
||
# 链接数据库
|
||
client = AsyncIOMotorClient('mongodb://localhost:27017')
|
||
db = client['zydm']
|
||
collection = db['zgqnb']
|
||
|
||
|
||
async def main():
|
||
collection_names = await db.list_collection_names()
|
||
# 判断数据表是否存在
|
||
if "zgqnb" not in collection_names:
|
||
print("中国青年报数据表不存在，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'
|
||
for p in soup.select("#content 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
|
||
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
|
||
for month in months:
|
||
if month < datetime(2024, 12, 1):
|
||
# 构造URL
|
||
url = f'https://zqb.cyol.com/html/{month.strftime("%Y-%m")}/period.xml'
|
||
"""https://zqb.cyol.com/html/2024-01/period.xml"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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.find("period_name").text.strip(), "%Y-%m-%d")
|
||
front_page = period.find("front_page").text.strip()
|
||
try:
|
||
url1 = f"https://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
|
||
"""https://zqb.cyol.com/html/2024-01/01/nbs.D110000zgqnb_01.htm"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
|
||
"href").replace("./", "").strip()
|
||
"""https://zqb.cyol.com/html/2024-01/01/nbs.D110000zgqnb_01.htm"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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')
|
||
for item2 in soup3.select("#titleList li a"):
|
||
url3 = f"https://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
|
||
"href").replace(
|
||
"./", "").strip()
|
||
"""https://zqb.cyol.com/html/2024-01/01/nw.D110000zgqnb_20240101_1-01.htm"""
|
||
if await collection.find_one({"detail_url": url3}, {"_id": False}):
|
||
continue
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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, 'html.parser')
|
||
try:
|
||
comments = soup4.find_all(
|
||
string=lambda text: isinstance(text, Comment))
|
||
for comment in comments:
|
||
if 'mpproperty' in comment:
|
||
enpproperty_content = comment.strip()
|
||
inner_soup = BeautifulSoup(enpproperty_content,
|
||
'html.parser')
|
||
# 提取特定标签值
|
||
title = inner_soup.find('title').text.strip()
|
||
perTitle = inner_soup.find(
|
||
'founder-introtitle').text.strip()
|
||
subTitle = inner_soup.find("founder-subtitle").text.strip()
|
||
author = inner_soup.find('author').text.strip()
|
||
except:
|
||
title = title
|
||
perTitle = ""
|
||
subTitle = ""
|
||
author = ""
|
||
content = await getContent(soup4)
|
||
await collection.insert_one({
|
||
"title": title,
|
||
"subtitle": subTitle,
|
||
"preTitle": perTitle,
|
||
"author": author,
|
||
"banmianming": banmianming,
|
||
"banmianhao": banmianhao,
|
||
'detail_url': url3,
|
||
'release_time': period_name,
|
||
'insert_timestamp': datetime.today(),
|
||
'content': content
|
||
})
|
||
crawl_num += 1
|
||
print(
|
||
f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(
|
||
f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(
|
||
f"中国青年报---{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',
|
||
'detail_url': url,
|
||
'release_time': period_name,
|
||
'insert_timestamp': datetime.today(),
|
||
'content': 'empty'}
|
||
)
|
||
else:
|
||
# 构造URL
|
||
url = f'https://zqb.cyol.com/pc/layout/{month.strftime("%Y%m")}/period.xml'
|
||
"""https://zqb.cyol.com/pc/layout/202501/period.xml"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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.find("period_name").text.strip(), "%Y-%m-%d")
|
||
front_page = period.find("front_page").text.strip()
|
||
try:
|
||
url1 = f"https://zqb.cyol.com/pc/layout/{period_name.strftime('%Y%m/%d')}/{front_page}"
|
||
"""https://zqb.cyol.com/pc/layout/202502/07/node_01.html"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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://zqb.cyol.com/pc/layout/{period_name.strftime('%Y%m/%d')}/" + item.get(
|
||
"href").replace("./", "").strip()
|
||
"""https://zqb.cyol.com/pc/layout/202502/07/node_01.html"""
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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')
|
||
for item2 in soup3.select(".news-list a"):
|
||
url3 = f"https://zqb.cyol.com/pc/" + item2.get(
|
||
"href").replace(
|
||
"../", "").strip()
|
||
"""https://zqb.cyol.com/pc/content/202502/07/content_406551.html"""
|
||
if await collection.find_one({"detail_url": url3}, {"_id": False}):
|
||
continue
|
||
title = item2.text.strip()
|
||
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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, 'html.parser')
|
||
try:
|
||
comments = soup4.find_all(
|
||
string=lambda text: isinstance(text, Comment))
|
||
for comment in comments:
|
||
if 'enpproperty' in comment:
|
||
# 提取注释内容
|
||
enpproperty_content = comment.strip()
|
||
inner_soup = BeautifulSoup(enpproperty_content,
|
||
'html.parser')
|
||
# 提取特定标签值
|
||
title = inner_soup.find('title').text.strip()
|
||
perTitle = inner_soup.find('introtitle').text.strip()
|
||
subTitle = inner_soup.find("subtitle").text.strip()
|
||
author = inner_soup.find('author').text.strip()
|
||
except:
|
||
title = title
|
||
perTitle = ""
|
||
subTitle = ""
|
||
author = ""
|
||
content = await getContent(soup4)
|
||
await collection.insert_one({
|
||
"title": title,
|
||
"subtitle": subTitle,
|
||
"preTitle": perTitle,
|
||
"author": author,
|
||
"banmianming": banmianming,
|
||
"banmianhao": banmianhao,
|
||
'detail_url': url3,
|
||
'release_time': period_name,
|
||
'insert_timestamp': datetime.today(),
|
||
'content': content
|
||
})
|
||
crawl_num += 1
|
||
print(
|
||
f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(
|
||
f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
|
||
await asyncio.sleep(random.randint(5, 15))
|
||
print(
|
||
f"中国青年报---{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"中国青年报采集完毕，共采集{crawl_num}条数据！")
|
||
|
||
|
||
asyncio.run(main())
|