赞
踩
目标网站:红网
爬取目的:为了获取某一地区更全面的在红网已发布的宣传新闻稿,同时也让自己的工作更便捷
环境:Pycharm2021,Python3.10,
安装的包:requests,csv,bs4,datetime
代码如下:(代码中附详细解析)
后续会不断完善,会出界面版,提高大家易用性;同时修改完善代码,设置为可指定获取的时间段的新闻稿。也会陆续更新其他新闻平台的新闻获取爬虫。
- #!/usr/bin/env python
- # -*- coding: utf-8 -*-
- # @Time : 2024/3/25 23:05
- # @Author : LanXiaoFang
- # @Site :
- # @File : redNet.py
- # @Software: PyCharm
- import csv
-
- import requests
- from bs4 import BeautifulSoup
- import datetime
-
- header = {
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
- 'Accept - Encoding': 'gzip, deflate, br',
- "Accept - Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
- 'Connection': "keep - alive",
- 'Referer': 'https://news-search.rednet.cn/Search?q=%E5%8F%8C%E7%89%8C',
- 'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:124.0) Gecko/20100101 Firefox/124.0",
- "Cookie": "wdcid=7486a2c50eaf8af8; Hm_lvt_c96b65e9975fa39afbd5e90222af5f39=1711378746,1711528844; Hm_lvt_aaecf8414f59c3fb0127932014cf53c7=1711378746,1711528844; __jsluid_s=56e0acf3607072cce852b9d4fc556f54; Hm_lpvt_c96b65e9975fa39afbd5e90222af5f39=1711528844; Hm_lpvt_aaecf8414f59c3fb0127932014cf53c7=1711528844; __jsl_clearance_s=1711530480.242|1|%2F%2BG2WNMEpLXiwlUgRr2hiMkP%2BMg%3D",
- "Upgrade-Insecure-Requests": "1",
- }
-
-
- def get_all_indexes(s, char):
- return [i for i, c in enumerate(s) if c == char]
-
-
- # 获取系统时间
- now = datetime.datetime.now()
- year = now.year # 年
- month = now.month # 月
- day = now.day # 日
-
- # 创建CSV文件并写入头部信息
- with open(str(month) + 'MTitleSP.csv', 'w', newline='', encoding='utf-8') as csvfile:
- writer = csv.writer(csvfile)
- writer.writerow(['序号', '新闻名称', '新闻来源', '媒体级别', '发布日期', '原文链接']) # 根据实际情况定义列名
- with open(str(month) + 'MTitleNSP.csv', 'w', newline='', encoding='utf-8') as csvfile:
- writer = csv.writer(csvfile)
- writer.writerow(['序号', '新闻名称', '新闻来源', '媒体级别', '发布日期', '原文链接']) # 根据实际情况定义列名
-
- article_no_sp = 1 # 用于计在标题含指定区域的存储的表中的数据的序号
- article_no = 1 # 用于计在标题不含但内容含指定区域的存储的表中的数据的序号
- get_go = 0 # 获取第几页开始的数据,现在是0开始
- count = 0 # 用于计算总共爬取的新闻数量
- area = '双牌' # 爬取指定区域的文章
-
- # 相当于满足条件就是一直循环
- while get_go >= 0:
-
- url = 'https://news-search.rednet.cn/Search?q=%E5%8F%8C%E7%89%8C&s=0&o=1&r=0&p=' + str(get_go)
- print(url)
- html = requests.get(url, headers=header)
- html.encoding = 'utf-8'
- get_go += 1
-
- if html.status_code == 200:
- soups = BeautifulSoup(html.text, 'html.parser')
- article_info = soups.find_all('div', class_='result')
- # print(len(article_info), '\n')
- for i in article_info:
- result_info = i.find_all('div', class_='result-info')
- station_source = result_info[0].select('span') # 选择result_info下的所有span标签
- station_info = station_source[0].text # 文章发布站点
- source_info = station_source[1].text # 文章来源
-
- print(station_info, source_info)
- # print(i.find_all('div', class_='title'), '\n')
- title_info = i.find_all('div', class_='title')
- # 文章链接
- article_href = title_info[0].a.get('href')
- if station_info[3:] == area + "新闻网":
- # print("双牌新闻网文章链接:", article_href, "---------", "https://moment.rednet.cn/pc" + article_href[22:])
- article_href = "https://moment.rednet.cn/pc" + article_href[22:]
- # 修改文章来源为红网时刻
- if 'rednet' in article_href:
- source_info = "红网"
- if 'moment.rednet' in article_href:
- source_info = "红网时刻"
- if '来源' in source_info:
- source_info = station_info[3:]
-
- # 文章标题
- article_title = title_info[0].h3.text
- # 获取发布时间
- article_up_time = title_info[0].span.text
-
- # 把显示为进入和昨天的时间,改为具体的日期
- if article_up_time == '今天':
- article_up_time = str(year) + '.' + str(month) + '.' + str(day)
- elif article_up_time == '昨天':
- article_up_time = str(year) + '.' + str(month) + '.' + str(day - 1)
- # 修改时间显示格式,-替换为.
- else:
- # article_up_time = article_up_time[:4] + '.' + article_up_time[5:7] + '.' + article_up_time[8:10] + '.'
- article_up_time = article_up_time.replace('-', '.')
- count += 1
- print(count, '----新闻名称', article_title, '文章来源', source_info, '发布日期', article_up_time, '原文链接',
- article_href)
- # 得到这篇文章发布的月份
- all_index = get_all_indexes(article_up_time, '.')
- article_up_time_month = article_up_time[all_index[0] + 1:all_index[1]]
- # 只要本月的,如果获取到的文章是本月之前的则不再获取,退出循环
- if int(article_up_time_month) < month:
- print('已经不是这个月的啦', int(article_up_time_month), month)
- get_go = -1
- break
-
- # 把数据存入表格 根据标题是否含有双牌两个字 分开存储
- if area in article_title:
- # 这个是标题含有双牌的
- with open(str(month) + 'MTitleSP.csv', 'a', newline='', encoding='utf-8') as csvfile:
- writer = csv.writer(csvfile)
- writer.writerow([article_no_sp, article_title, source_info, '省级', article_up_time, article_href])
- article_no_sp += 1
- else:
- # 这个是标题不含但是内容含有双牌的
- with open(str(month) + 'MTitleNSP.csv', 'a', newline='', encoding='utf-8') as csvfile:
- writer = csv.writer(csvfile)
- writer.writerow([article_no, article_title, '省级', source_info, article_up_time, article_href])
- article_no += 1
由于现在是2024年4月1日 13:04,文章更新的本月的不多。
运行结果如下:
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。