138 lines
6.2 KiB
Python
138 lines
6.2 KiB
Python
# _*_ coding : UTF-8 _*_
|
||
# @Time : 2024/01/09 14:15
|
||
# @UpdateTime : 2024/01/09 16:30
|
||
# @Author : Haochen Zhong
|
||
# @File : CrawlSiChuan.py
|
||
# @Software : PyCharm
|
||
# @Comment : 本程序采集四川日报数字报板面数据
|
||
|
||
import re
|
||
from bs4 import BeautifulSoup
|
||
import requests
|
||
from datetime import timedelta, datetime
|
||
import time
|
||
import pymongo
|
||
import random
|
||
|
||
# 数据库起止时间
|
||
start_date = datetime.strptime('2021-12-31', '%Y-%m-%d')
|
||
end_date = datetime.today()
|
||
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'}
|
||
# 创建数据库
|
||
client = pymongo.MongoClient('localhost', 27017)
|
||
mydb = client.dfdm_sjribao
|
||
sichuanribao = mydb.sichuanribao
|
||
|
||
|
||
def main():
|
||
# 判断数据库是否存在
|
||
collist = mydb.list_collection_names()
|
||
if "sichuanribao" in collist: # 检测集合是否存在
|
||
print("四川日报集合存在，更新数据库")
|
||
# 数据库最新一条内容的时间
|
||
db_time = sichuanribao.find_one(sort=[('release_time', -1)])[
|
||
'release_time'] # 或者find().sort('_id', -1).limit(1)
|
||
print('数据库截止时间%s' % db_time)
|
||
# 输入更新数据库时间
|
||
input_time = datetime.today()
|
||
if db_time < input_time:
|
||
getData(db_time, input_time)
|
||
else:
|
||
print('数据库无需更新')
|
||
else:
|
||
# 爬取网页并建立数据库
|
||
print("数据库不存在，建立数据库！")
|
||
getData(start_date, end_date)
|
||
|
||
|
||
def getContent(soup):
|
||
content = ''
|
||
for p in soup.select('#main2 > div.main2_r > ul > li:nth-child(2) p'):
|
||
para = p.text.strip()
|
||
if para:
|
||
content += para
|
||
content += '\n'
|
||
return content
|
||
|
||
|
||
def getSubtitle(soup):
|
||
subtitle = ''
|
||
if soup.select('#main2 > div.main2_r > ul > li:nth-child(1) > h2:nth-child(1)'):
|
||
for p in soup.select('#main2 > div.main2_r > ul > li:nth-child(1) > h2:nth-child(1)'):
|
||
para = p.text.strip()
|
||
if para:
|
||
subtitle += para
|
||
subtitle += '\n'
|
||
return subtitle
|
||
|
||
|
||
def getData(start_date, end_date):
|
||
crawl_num = 0
|
||
for i in range((end_date - start_date).days):
|
||
date_now = start_date + timedelta(days=i + 1)
|
||
date_now_s = date_now.strftime('%Y%m%d')
|
||
base_url = "https://epaper.scdaily.cn/shtml/scrb/"
|
||
url = base_url + date_now_s + '/index.shtml'
|
||
try:
|
||
response = requests.get(url, headers)
|
||
print(f"一级链接状态：{response.status_code}")
|
||
if response.status_code == 200:
|
||
response.encoding = response.apparent_encoding
|
||
soup = BeautifulSoup(response.text, "lxml")
|
||
for item in soup.select("#main > div.main_r > ul:nth-child(2) > li:nth-child(2) a"):
|
||
banmianhao = item.text.split("：")[0]
|
||
banmianming = item.text.split("：")[-1]
|
||
url1 = "https://epaper.scdaily.cn" + item.get("href")
|
||
response2 = requests.get(url1, headers)
|
||
print(f"二级链接状态：{response2.status_code}")
|
||
if response2.status_code == 200:
|
||
response2.encoding = response2.apparent_encoding
|
||
soup2 = BeautifulSoup(response2.text, "lxml")
|
||
for item2 in soup2.select("#main > div.main_r > ul:nth-child(3) > li:nth-child(2) a"):
|
||
url2 = "https://epaper.scdaily.cn" + item2.get("href")
|
||
title = item2.get("title")
|
||
response3 = requests.get(url2, headers)
|
||
print(f"三级连接状态：{response3.status_code}")
|
||
if response3.status_code == 200:
|
||
response3.encoding = response3.apparent_encoding
|
||
soup3 = BeautifulSoup(response3.text, "lxml")
|
||
content = getContent(soup3)
|
||
subtitle = getSubtitle(soup3)
|
||
sichuanribao.insert_one({'banmianhao': banmianhao,
|
||
'banmianming': banmianming,
|
||
'title': title,
|
||
'subtitle': subtitle,
|
||
'h3title': '',
|
||
'author': '',
|
||
'keywordlist': '',
|
||
'detail_url': url2,
|
||
'release_time': date_now,
|
||
'insert_timestamp': datetime.today(),
|
||
'content': content})
|
||
print(f"四川日报--{date_now_s}-{banmianhao}-{title}----已完成")
|
||
crawl_num += 1
|
||
time.sleep(random.randint(3, 10))
|
||
print(f"四川日报--{date_now_s}-{banmianhao}----已完成")
|
||
time.sleep(random.randint(3, 10))
|
||
print(f"四川日报--{date_now_s}-----已完成")
|
||
time.sleep(random.randint(3, 10))
|
||
except Exception as result:
|
||
sichuanribao.insert_one({'banmianhao': 'empty',
|
||
'banmianming': 'empty',
|
||
'preTitle': 'empty',
|
||
'title': 'empty',
|
||
'subtitle': 'empty',
|
||
'author': 'empty',
|
||
'keywordlist': 'empty',
|
||
'detail_url': url,
|
||
'release_time': date_now,
|
||
'insert_timestamp': datetime.today(),
|
||
'content': 'empty'})
|
||
print(result)
|
||
print(f"四川日报采集完毕，共采集{crawl_num}条数据！")
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|