作业来源:https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3002
0.从新闻url获取点击次数,并整理成函数
- newsUrl
- newsId(re.search())
- clickUrl(str.format())
- requests.get(clickUrl)
- re.search()/.split()
- str.lstrip(),str.rstrip()
- int
- 整理成函数
- 获取新闻发布时间及类型转换也整理成函数
1.从新闻url获取新闻详情: 字典,anews
2.从列表页的url获取新闻url:列表append(字典) alist
3.生成所页列表页的url并获取全部新闻 :列表extend(列表) allnews
import requests from bs4 import BeautifulSoup from datetime import datetime import locale import re locale.setlocale(locale.LC_CTYPE,'chinese') def getClickCount(newsUrl): newsId = re.findall('\_(.*).html', newsUrl)[0].split('/')[1] #使用正则表达式取得新闻编号 clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) clickStr = requests.get(clickUrl).text return(re.search("hits').html('(.*)');",clickStr).group(1)) def getNewsContent(content): f = open('gzccNews.txt','a',encoding='utf8') f.write(content) f.close() def getNewDetail(newsUrl): resd = requests.get(newsUrl) # 返回response resd.encoding = 'utf-8' soupd = BeautifulSoup(resd.text, 'html.parser') print('标题:' + soupd.select('.show-title')[0].text) print('链接:'+newsUrl) newsUrl = newsUrl info = soupd.select('.show-info')[0].text time = re.search('发布时间:(.*) xa0xa0 xa0xa0作者:', info).group(1) dtime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S') if info.find('作者:') > 0: author = info[info.find('作者:'):].split()[0].lstrip('作者:') else: author = '无' if info.find('审核:') > 0: check = info[info.find('审核:'):].split()[0].lstrip('审核:') else: check = '无' if info.find('来源:') > 0: source = info[info.find('来源:'):].split()[0].lstrip('来源:') else: sourec = '无' if info.find('摄影:') > 0: photo = info[info.find('摄影:'):].split()[0].lstrip('摄影:') else: photo = '无' print('发布时间:{} 作者:{} 审核:{} 来源:{} 摄影:{}'.format(dtime,author,check,source,photo)) clickCount = getClickCount(newsUrl) print('点击次数:' + clickCount) content = soupd.select('.show-content')[0].text getNewsContent(content) # print(content) def getLiUrl(ListPageUrl): res = requests.get(ListPageUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text,'html.parser') # print(soup.select('li')) for news in soup.select('li'): if len(news.select('.news-list-title'))>0: a = news.a.attrs['href'] getNewDetail(a) firstUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' print('第1页:') getLiUrl(firstUrl) res = requests.get(firstUrl) res.encoding = 'utf-8' soupn = BeautifulSoup(res.text,'html.parser') n = int(soupn.select('.a1')[0].text.rstrip('条'))//10+1 # for i in range(2,n): # pageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) # print('第{}页:'.format(i)) # getLiUrl(pageUrl) # break
运行截图:
4.设置合理的爬取间隔
import time
import random
time.sleep(random.random()*3)
#设置合理的爬取间隔 for i in range(5): time.sleep(random.random()*3)
5.用pandas做简单的数据处理并保存
保存到csv或excel文件
newsdf.to_csv(r'F:duym爬虫gzccnews.csv')
#保存文件 pd.Series(allnews) newsdf=pd.DataFrame(allnews) newsdf.to_csv(r'F: ews.csv')
截图: