1.取出一个新闻列表页的全部新闻 包装成函数。
2.获取总的新闻篇数,算出新闻总页数。
3.获取全部新闻列表页的全部新闻详情。
4.找一个自己感兴趣的主题,进行数据爬取,并进行分词分析。不能与其它同学雷同。
1-3:
import requests from bs4 import BeautifulSoup from datetime import datetime import re listPageUrl = "http://news.gzcc.cn/html/xiaoyuanxinwen/" page = 1 headers = {‘User-Agent‘: ‘User-Agent:Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 ‘ ‘(KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36‘} # 获取新闻点击次数 def getNewsId(url): newsId = re.findall(r‘\_(.*).html‘, url)[0][-4:] clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId) clickRes = requests.get(clickUrl,headers) # 利用正则表达式获取新闻点击次数 clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1)) return clickCount # 读取新闻细节 def getNewDetail(detail,title,description): resDescript = requests.get(detail,headers) resDescript.encoding = "utf-8" soupDescript = BeautifulSoup(resDescript.text, ‘html.parser‘) content = soupDescript.select(".show-content")[0].text # 正文 info = soupDescript.select(".show-info")[0].text # info相关内容 # 第一种方法 分离 message = info.split() # 第二种方法 用正则表达式 print(‘标题‘ + ‘: ‘ + title) print(‘概要‘ + ‘: ‘ + description) print(‘链接‘ + ‘: ‘ + detail) print(‘正文‘ + ‘ :‘ + content) if(re.search("发布时间:(.*) \xa0\xa0 \xa0\xa0作者:", info) !="Null" ): time = re.search("发布时间:(.*) \xa0\xa0 \xa0\xa0作者:", info).group(1) if (re.search("作者:(.*)\xa0\xa0审核:", info) !="Null"): author = re.search("作者:(.*)\xa0\xa0审核:", info).group(1) print("作者:" + author) if (re.search("审核:(.*)\xa0\xa0来源:", info) !="Null"): right = re.search("审核:(.*)\xa0\xa0来源:", info).group(1) if (re.search(‘来源:(.*)\xa0\xa0\xa0\xa0摄影:‘, info) != "null"): resource = re.search(‘来源:(.*)\xa0\xa0\xa0\xa0摄影:‘, info) if (re.search("摄影:(.*)\xa0\xa0\xa0\xa0点击:", info)!="Null"): video = re.search("摄影:(.*)\xa0\xa0\xa0\xa0点击:", info) count = getNewsId(detail) dateTime = datetime.strptime(time, ‘%Y-%m-%d %H:%M:%S‘) #获取新闻 def getListPage(listPageUrl,n): resListPage = requests.get(listPageUrl,headers) resListPage.encoding = "utf-8" soup = BeautifulSoup(resListPage.text, ‘html.parser‘) PageUrl = listPageUrl + str(1) + ".html" if(n == 0): global page page=int(soup.select(".a1")[0].text[:-1]) print(page) for s in soup.select("li"): if len(s.select(".news-list-title"))>0: title = s.select(".news-list-title")[0].text #新闻标题 description = s.select(".news-list-description")[0].text #新闻描述 detail = s.a.attrs["href"] #观看新闻细节 getNewDetail(detail,title,description) getListPage(listPageUrl,0) print(page) for n in range(1,page): PageUrl = listPageUrl + str(n) + ".html" getListPage(PageUrl,n) # for n in range(1,soup.select(".a1")[0].text[:-1]): # PageUrl = listPageUrl+str(n)+"html"; getListPage(PageUrl) ‘‘‘ ‘‘‘
4(爬慕课网):
import requests,jieba from bs4 import BeautifulSoup import re #网站 慕课网 url = "https://www.imooc.com/course/list" resDescript = requests.get(url) resDescript.encoding = "utf-8" soupDescript = BeautifulSoup(resDescript.text, ‘html.parser‘) #全局变量 n =1 m =1 notelist = "" #错误词汇 delete_word={‘使‘,‘D‘,‘b‘,‘e‘,‘f‘,‘t‘,‘C‘,‘的‘,‘o‘,‘,‘,‘a‘,‘A‘,‘n‘,‘S‘,‘y‘,‘i‘,‘了‘,‘。‘} #分析数据的方向、类型、类别 for s in soupDescript.select(".course-nav-item.on"): if n == 1 : print("方向:" + s.text) elif n ==2:print("类型:" + s.text) elif n ==3:print("类别:"+s.text) n = n+1 #分析数据的受欢迎类型、难度 for q in soupDescript.select(".sort-item.active"): if m == 1 : print("受欢迎类型:"+q.text) else: print("难度:"+q.text) m=m+1 #挖掘课程的相关信息 for content in soupDescript.select(".course-card-container"): img = content.select(".course-banner.lazy")[0].attrs["src"][2:] name = content.select(".course-card-name")[0].text desc = content.select(".course-card-desc")[0].text notelist += desc notelist+=name print("图片链接:"+img) print("课程名字:"+name) print("简介:"+desc) print("\n") NoteDic={} for i in set(notelist): #计算次数 NoteDic[i]=notelist.count(i) for i in delete_word: #删除非法词汇 if i in NoteDic: del NoteDic[i] #进行排序 sort_word = sorted(NoteDic.items(), key = lambda d:d[1], reverse = True) # 由大到小排序 #输出效果 print(sort_word)
原文地址:https://www.cnblogs.com/huangzemian123/p/9147852.html
时间: 2024-10-12 10:33:56