1. 将新闻的正文内容保存到文本文件。
def writeNewsDetail(newid,content): f=open(newid+'.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 re import requests from bs4 import BeautifulSoup from datetime import datetime def getClickCount(newsUrl): newId=re.search("/(d*).html$",newsUrl).group(1) clickUrl ="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId) resc = requests.get(clickUrl) num = re.search(".html('(d*)')",resc.text).group(1) return int(num,10) def getNewDetail(newsUrl): res1 = requests.get(newsUrl) res1.encoding = 'utf-8' soup1 = BeautifulSoup(res1.text, 'html.parser') #标题 title=soup1.select_one(".show-title").text # 正文 content = soup1.select_one("#content").text info = soup1.select_one(".show-info").text # 发布时间 time = datetime.strptime(info.lstrip("发布时间:")[:19], "%Y-%m-%d %H:%M:%S") # 作者 author = info[info.find("作者:"):].split()[0].lstrip("作者:") # 来源 x = info.find("来源:") if x >= 0: source = info[x:].split()[0].lstrip("来源:") else: source = "" # 摄影 x = info.find("摄影:") if x >= 0: shot = info[x:].split()[0].lstrip("摄影:") else: shot = "" return {"title":title,"content":content,"time":time,"author":author,"source":source,"shot":shot,"count":getClickCount(newsUrl)} def getnewsls(newslsUrl): newsls=[]; res = requests.get(newslsUrl) res.encoding='utf-8' soup = BeautifulSoup(res.text, 'html.parser') a = soup.select_one(".news-list").select("a") for i in a: url = i.attrs.get('href') newsls.append(getNewDetail(url)) return newsls def getPageNum(newstotalUrl): res = requests.get(newstotalUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') a = soup.select_one("#pages").select("a")[-2] return int(a.text,10) def getnewstotal(newstotalUrl): newstotal=[]; pageNum=getPageNum(newstotalUrl) newstotal.extend(getnewsls(newstotalUrl)) for i in range(2,pageNum+1): newstotal.extend(getnewsls("http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i))) return newstotal newstotal=getnewstotal("http://news.gzcc.cn/html/xiaoyuanxinwen/")
3. 安装pandas,用pandas.DataFrame(newstotal),创建一个DataFrame对象df.
df = pandas.DataFrame(newsTotal)
4. 通过df将提取的数据保存到csv或excel 文件。
df.to_excel('newsData.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(df[['click', 'title', 'sources']].head(6)) print(df[(df['click'] > 3000) & (df['sources'] == '学校综合办')]) sou = ['国际学院', '学生工作处'] print(df[df['sources'].isin(sou)])