学习了《python网络爬虫实战》第一个爬虫,爬取新浪新闻
请安装anaconda,其中附带的spyder方便运行完查看变量 1.进入cmd控制台, 输入 pip install BeautifulSoup4 pip install requests 2.编写代码,代码已经很清晰了,直接运行不会报错并有成功的结果 def getNewsDetail(newsUrl): import requests from bs4 import BeautifulSoup from datetime import datetime newsWeb = requests.get(newsUrl) newsWeb.encoding = 'utf-8' soup = BeautifulSoup(newsWeb.text,'lxml') result = {} result['title'] = soup.select('.main-title')[0].text result['newsSource'] = soup.select('.source')[0].text timeSource = soup.select('.date')[0].text result['datetime'] = datetime.strptime(timeSource,'%Y年%m月%d日 %H:%M') result['article'] = soup.select('.article')[0].text result['editor'] = soup.select('.show_author')[0].text.strip('责任编辑:') result['comment'] = soup.select('.num')[0].text return result def parseListLinks(url): import requests import json newsDetails = [] request = requests.get(url) jsonLoad = json.loads(request.text.lstrip(' newsloadercallback(').rstrip(');')) newsUrls = [] for item in jsonLoad['result']['data']: newsUrls.append(item['url']) for url in newsUrls: newsDetails.append(getNewsDetail(url)) return newsDetails if __name__ == '__main__': #获取单个新闻页面的信息 newsUrl = 'http://news.sina.com.cn/s/wh/2018-01-08/doc-ifyqkarr7830426.shtml' newsDetail = getNewsDetail(newsUrl) #获取整个列表各个新闻页面的信息 rollUrl='http://api.roll.news.sina.com.cn/zt_list?channel=news&cat_1=gnxw\ &cat_2==gdxw1||=gatxw||=zs-pl||=mtjj&level==1||=2&show_ext=1&show_all=1&\ show_num=22&tag=1&format=json&page=23&callback=newsloadercallback&_=1515911333929' newsDetails = parseListLinks(rollUrl)