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。
import requests from bs4 import BeautifulSoup from datetime import datetime import re # 获取新闻点击次数 def getNewsId(url): newsId = re.search(r'\_\d{4}\/((.*)).html', url).group(1) clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) clickRes = requests.get(clickUrl) # 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 # 获取新闻细节 def getNewsDetail(newsUrl): resd = requests.get(newsUrl) resd.encoding = 'utf-8' soupd = BeautifulSoup(resd.text, 'html.parser') content = soupd.select('#content')[0].text info = soupd.select('.show-info')[0].text # 调用getNewsId()获取点击次数 count = getNewsId(newsUrl) # 识别时间格式 date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1) # 识别一个至三个数据 if(info.find('作者：')>0): author = re.search('作者：((.{2,4}\s|.{2,4}、|\w*\s){1,3})', info).group(1) else: author = '无' if(info.find('审核：')>0): check = re.search('审核：((.{2,4}\s){1,3})', info).group(1) else: check = '无' if(info.find('来源：')>0): sources = re.search('来源：(.*)\s*摄|点', info).group(1) else: sources = '无' if (info.find('摄影：') > 0): photo = re.search('摄影：(.*)\s*点', info).group(1) else: photo = '无' # 用datetime将时间字符串转换为datetime类型 dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S') # 利用format对字符串进行操作 print('发布时间：{0}\n作者：{1}\n审核：{2}\n来源：{3}\n摄影：{4}\n点击次数：{5}'.format(dateTime, author, check, sources, photo, count)) print(content) def getListPage(listUrl): res = requests.get(listUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') for new in soup.select('li'): if len(new.select('.news-list-title')) > 0: title = new.select('.news-list-title')[0].text description = new.select('.news-list-description')[0].text newsUrl = new.select('a')[0]['href'] print('标题:{0}\n内容:{1}\n链接:{2}'.format(title, description, newsUrl)) # 调用getNewsDetail()获取新闻详情 getNewsDetail(newsUrl) break listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' getListPage(listUrl) res = requests.get(listUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') listCount = int(soup.select('.a1')[0].text.rstrip('条'))//10+1 for i in range(2,listCount): listUrl= 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) getListPage(listUrl)
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。
爬取网易科技频道IT专题：
代码：
import requests, re, jieba from bs4 import BeautifulSoup from datetime import datetime # 获取新闻细节 def getNewsDetail(newsUrl): resd = requests.get(newsUrl) resd.encoding = 'gb2312' soupd = BeautifulSoup(resd.text, 'html.parser') content = soupd.select('#endText')[0].text info = soupd.select('.post_time_source')[0].text date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1) # 识别时间格式 dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S') # 用datetime将时间字符串转换为datetime类型 sources = re.search('来源:\s*(.*)', info).group(1) keyWords = getKeyWords(content) print('发布时间：{0}\n来源：{1}'.format(dateTime, sources)) print('关键词：{}、{}、{}'.format(keyWords[0], keyWords[1], keyWords[2])) print(content) # 通过jieba分词，获取新闻关键词 def getKeyWords(content): content = ''.join(re.findall('[\u4e00-\u9fa5]', content)) # 通过正则表达式选取中文字符数组，拼接为无标点字符内容 wordSet = set(jieba._lcut(content)) wordDict = {} for i in wordSet: wordDict[i] = content.count(i) deleteList, keyWords = [], [] for i in wordDict.keys(): if len(i) < 2: deleteList.append(i) # 去掉单字无意义字符 for i in deleteList: del wordDict[i] dictList = list(wordDict.items()) dictList.sort(key=lambda item: item[1], reverse=True) # 排序，返回前三关键字 for i in range(3): keyWords.append(dictList[i][0]) return keyWords # 获取一页的新闻 def getListPage(listUrl): res = requests.get(listUrl) res.encoding = 'gbk' soup = BeautifulSoup(res.text, 'html.parser') for new in soup.select('#news-flow-content')[0].select('li'): newsUrl = new.select('a')[0]['href'] title = new.select('a')[0].text print('标题：{0}\n链接：{1}'.format(title, newsUrl)) getNewsDetail(newsUrl) # 调用getNewsDetail()获取新闻详情 break # z只获取单个新闻，若要获取整页则去掉break listUrl = 'http://tech.163.com/it/' getListPage(listUrl) # 获取首页新闻 for i in range(2, 20): # 因为网易新闻频道只存取20页新闻，直接设置20 listUrl = 'http://tech.163.com/special/it_2016_%02d/' % i # 填充新闻页，页面格式为两位数字字符 getListPage(listUrl)
结果截图：
