1. 将新闻的正文内容保存到文本文件。
def file(content): f = open('news.txt','a',encoding='utf-8') f.write(content) f.close()
2. 将新闻数据结构化为字典的列表:
- 单条新闻的详情-->字典news
- 一个列表页所有单条新闻汇总-->列表newsls.append(news)
- 所有列表页的所有新闻汇总列表newstotal.extend(newsls)
import requests from bs4 import BeautifulSoup import datetime import re import pandas def getClickCount(newUrl): re1 = re.search('\_(.*).html',newUrl) re2 = re.match('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html',newUrl) i = re1.group(1).split('/')[-1] cUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(i) res = requests.get(cUrl) res2 = int(res.text.split(".html")[-1].lstrip("('").rstrip("');")) return(res2) def file(content): f = open('news.txt','a',encoding='utf-8') f.write(content) f.close() def getInformation(a1): res1 = requests.get(a1) res1.encoding = 'utf-8' soup1 = BeautifulSoup(res1.text, 'html.parser') new = {} new['title'] = soup1.select(".show-title")[0].text #new['content'] = soup1.select("#content")[0].text #file(new['content']) about = soup1.select('.show-info')[0].text time = about.lstrip('发布时间:')[:19] new['time'] = datetime.datetime.strptime(time, '%Y-%m-%d %H:%M:%S') if about.find('来源:') > 0: new['origin'] = about[about.find('来源:'):].split()[0].lstrip("来源:") else: new['origin'] = "未知" if about.find('作者:') > 0: new['writer'] = about[about.find('作者:'):].split()[0].lstrip("作者:") else: new['writer'] = "佚名" if about.find('审核:') > 0: new['audit'] = about[about.find('审核:'):].split()[0].lstrip("审核:") else: new['audit'] = "佚名" if about.find('摄影:') > 0: new['photograph'] = about[about.find('摄影:'):].split()[0].lstrip("摄影:") else: new['photograph'] = "佚名" new['url'] = a1 new['count'] = getClickCount(a1) return(new) def getnewslist(url): resurl = requests.get(url) resurl.encoding = 'utf-8' soup = BeautifulSoup(resurl.text, 'html.parser') a = soup.select('li') list = [] for news in a: if len(news.select('.news-list-title')) > 0: a1 = news.select('a')[0].attrs['href'] list.append(getInformation(a1)) return (list) def getPage(url): res = requests.get(url) res.encoding = 'utf-8' soup = BeautifulSoup(res.text,'html.parser') n = int(soup.select('.a1')[0].text.rstrip('条'))//10+1 return(n) url = "http://news.gzcc.cn/html/xiaoyuanxinwen/" newTotal = [] newTotal.extend(getnewslist(url)) n = getPage(url) print(n) for i in range(n,n+1): urls = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i) newTotal.extend(getnewslist(urls))
3. 安装pandas,用pandas.DataFrame(newstotal),创建一个DataFrame对象df.
4. 通过df将提取的数据保存到csv或excel 文件。
dt = pandas.DataFrame(newTotal) dt.to_excel('new.xlsx')
5. 用pandas提供的函数和方法进行数据分析:
- 提取包含点击次数、标题、来源的前6行数据
- 提取‘学校综合办’发布的,‘点击次数’超过3000的新闻。
- 提取'国际学院'和'学生工作处'发布的新闻。
print(dt.head(6)) print(dt[(dt['count'] > 700)&(dt['origin']=='学校综合办')]) sou = ['国际学院', '学生工作处'] print(dt[dt['origin'].isin(sou)])