141 lines
6.5 KiB
Python
141 lines
6.5 KiB
Python
|
# _*_ coding : UTF-8 _*_
|
|||
|
|
# @Time : 2022/12/27 14:15
|
|||
|
|
# @UpdateTime : 2023/11/08 16:30
|
|||
|
|
# @Author : Haochen Zhong
|
|||
|
|
# @File : CrawlGuizhou.py
|
|||
|
|
# @Software : PyCharm
|
|||
|
|
# @Comment : 本程序采集贵州日报数字报板面数据
|
|||
|
|
import random
|
|||
|
|
import time
|
|||
|
|
from datetime import timedelta, datetime
|
|||
|
|
|
|||
|
|
import pymongo
|
|||
|
|
import requests
|
|||
|
|
from bs4 import BeautifulSoup
|
|||
|
|
|
|||
|
|
# 数据库起止时间
|
|||
|
|
start_date = datetime.strptime('2021-12-31', '%Y-%m-%d')
|
|||
|
|
"""贵州日报数字报2022-01-01开始有数据纪录"""
|
|||
|
|
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
|
|||
|
|
guizhouribao = mydb.guizhouribao
|
|||
|
|
# 设置随机时间
|
|||
|
|
sleeptime = random.randint(2, 15)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
# 判断数据库是否存在
|
|||
|
|
collist = mydb.list_collection_names()
|
|||
|
|
if "guizhouribao" in collist: # 检测集合是否存在
|
|||
|
|
print("贵州集合存在，更新数据库")
|
|||
|
|
# 数据库最新一条内容的时间
|
|||
|
|
db_time = guizhouribao.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 get_content(soup3):
|
|||
|
|
content = ""
|
|||
|
|
for p in soup3.select("#ozoom p"):
|
|||
|
|
para = p.text.strip()
|
|||
|
|
if para:
|
|||
|
|
content += para
|
|||
|
|
content += '\n'
|
|||
|
|
return content
|
|||
|
|
|
|||
|
|
|
|||
|
|
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 = "http://szb.gzrbs.com.cn/pc/layout/" + date_now_s + "/"
|
|||
|
|
url = base_url + "node_01.html"
|
|||
|
|
# http://szb.gzrbs.com.cn/pc/layout/202201/01/node_01.html
|
|||
|
|
try:
|
|||
|
|
response = requests.get(url=url, headers=headers, timeout=(30, 45))
|
|||
|
|
response.encoding = response.apparent_encoding
|
|||
|
|
print(f"一级连接状态：{response.status_code}")
|
|||
|
|
if response.status_code == 200:
|
|||
|
|
soup = BeautifulSoup(response.text, "lxml")
|
|||
|
|
for item in soup.select(".btn-block"):
|
|||
|
|
banmianming = item.text.split("：")[-1]
|
|||
|
|
banmianhao = item.text.split("：")[0]
|
|||
|
|
url1 = base_url + item.get("href")
|
|||
|
|
response2 = requests.get(url=url1, headers=headers, timeout=(30, 45))
|
|||
|
|
response2.encoding = response2.apparent_encoding
|
|||
|
|
print(f"二级连接状态：{response2.status_code}")
|
|||
|
|
if response2.status_code == 200:
|
|||
|
|
soup2 = BeautifulSoup(response2.text, "lxml")
|
|||
|
|
for item2 in soup2.select(".resultList a"):
|
|||
|
|
title = item2.text.strip()
|
|||
|
|
url2 = "http://szb.gzrbs.com.cn/pc/" + item2.get("href")[9:]
|
|||
|
|
# http://szb.gzrbs.com.cn/pc/cont/202201/02/content_42202.html
|
|||
|
|
response3 = requests.get(url=url2, headers=headers, timeout=(30, 45))
|
|||
|
|
response3.encoding = response3.apparent_encoding
|
|||
|
|
print(f"三级连接状态：{response3.status_code}")
|
|||
|
|
if response3.status_code == 200:
|
|||
|
|
soup3 = BeautifulSoup(response3.text, "lxml")
|
|||
|
|
try:
|
|||
|
|
title = soup3.select("#Title")[0].text.strip()
|
|||
|
|
except:
|
|||
|
|
title = title
|
|||
|
|
try:
|
|||
|
|
subtitle = soup3.select("#SubTitle")[0].text.strip()
|
|||
|
|
except:
|
|||
|
|
subtitle = ""
|
|||
|
|
try:
|
|||
|
|
preTitle = soup3.select("#PreTitle")[0].text.strip()
|
|||
|
|
except:
|
|||
|
|
preTitle = ""
|
|||
|
|
content = get_content(soup3)
|
|||
|
|
guizhouribao.insert_one({'banmianhao': banmianhao,
|
|||
|
|
'banmianming': banmianming,
|
|||
|
|
'preTitle': preTitle,
|
|||
|
|
'title': title,
|
|||
|
|
'subtitle': subtitle,
|
|||
|
|
'author': '',
|
|||
|
|
'keywordlist': 'empty',
|
|||
|
|
'detail_url': url2,
|
|||
|
|
'release_time': date_now,
|
|||
|
|
'insert_timestamp': datetime.today(),
|
|||
|
|
'content': content})
|
|||
|
|
crawl_num += 1
|
|||
|
|
print(f"贵州日报-{date_now_s}-{banmianming}-{title}-已完成")
|
|||
|
|
time.sleep(sleeptime)
|
|||
|
|
print(f"贵州日报-{date_now_s}-{banmianming}-已完成")
|
|||
|
|
time.sleep(sleeptime)
|
|||
|
|
print(f"贵州日报-{date_now_s}-已完成")
|
|||
|
|
except Exception as result:
|
|||
|
|
guizhouribao.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"贵州日报采集完毕，共采集{crawl_num}条数据！")
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == '__main__':
|
|||
|
|
main()
|