1. 用requests库和BeautifulSoup库,爬取校园新闻首页新闻的标题、链接、正文、show-info。
2. 分析info字符串,获取每篇新闻的发布时间,作者,来源,摄影等信息。
3. 将字符串格式的发布时间转换成datetime类型
4. 使用正则表达式取得新闻编号
5. 生成点击次数的Request URL
6. 获取点击次数
7. 将456步骤定义成一个函数 def getClickCount(newsUrl):
8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
9. 尝试用使用正则表达式分析show info字符串,点击次数字符串。
import requests from bs4 import BeautifulSoup from datetime import datetime import locale import re locale.setlocale(locale.LC_CTYPE, 'chinese') url = "http://news.gzcc.cn/html/xiaoyuanxinwen/" res = requests.get(url) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') def getClickCount(newsUrl): newsid = re.search(r"\_(.*).html", newsUrl).group(1)[-4:] clicktimesurl = ("http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80").format(newsid) clicktimes = int(requests.get(clicktimesurl).text.split(".html(")[-1].lstrip("'").rstrip("');")) return clicktimes def getNewsDetail(newsUrl): resdet = requests.get(newsUrl) resdet.encoding = 'utf-8' soupdet = BeautifulSoup(resdet.text, 'html.parser') contentdetail = soupdet.select('#content')[0].text showinfo = soupdet.select('.show-info')[0].text date = showinfo.lstrip("发布时间:")[:19] author = re.search('作者:((.{2,4}s){1,3})', showinfo).group(1) checker = re.search('审核:((.{2,4}s){1,3})', showinfo).group(1) source = re.search('来源:((.{2,20}s){1,3})', showinfo).group(1) clicktimes = getClickCount(address) dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S') print("发表时间:{0} 作者:{1} 审核:{2} 来源:{3} 点击次数:{4} 次".format(dateTime, author, checker, source, clicktimes)) print(contentdetail) for news in soup.select('li'): if len(news.select('.news-list-title')) > 0: title = news.select('.news-list-title')[0].text description = news.select('.news-list-description')[0].text info = news.select('.news-list-info')[0].text address = news.select('a')[0]['href'] print(" 标题: {0} 描述: {1} 信息: {2} 链接: {3}".format(title, description, info, address)) getNewsDetail(address)