#author: Jingke
from bs4 import BeautifulSoup
import ssl
from urllib.request import Request, urlopen
import urllib.request


class Scrape_news():
   @classmethod
   def url_link(cls, url, *args, **kwargs):
       ssl._create_default_https_context = ssl._create_unverified_context
       opener = urllib.request.build_opener()
       opener.addheaders = [('User-Agent',
                             'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
       urllib.request.install_opener(opener)
       req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})

       web = urlopen(req)
       bsObj = BeautifulSoup(web)
       news = bsObj.find_all(*args, **kwargs)

       list = []
       for new in news:
           list.append(new.get('href'))

       l=[]
       for i in list:
           if "articles" in i:
               i = "http://www.qdaily.com/" + i
               l.append(i)
       print(l)
       return l


if __name__ == '__main__':
   # Scrape_news.url_link('http://www.qdaily.com', "h3", {"class": "smart-dotdotdot"})
   Scrape_news.url_link('http://www.qdaily.com', "a")

------------------------------------------------------------------------------------------------------------------#

#author: Jingke

class Scrape_news():
    @classmethod
    def url_link(cls, url, *args, **kwargs):
        ssl._create_default_https_context = ssl._create_unverified_context
        opener = urllib.request.build_opener()
        opener.addheaders = [('User-Agent',
                              'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
        urllib.request.install_opener(opener)
        req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})

        web = urlopen(req)
        bsObj = BeautifulSoup(web)
        news = bsObj.find_all(*args, **kwargs)

        list=[]
        for new in news:
            list.append(new.get_text())
        print(list)
        return list


if __name__ == '__main__':
    Scrape_news.url_link('http://www.qdaily.com', "h3", {"class": "smart-dotdotdot"})

result:
['重新认识人性的可能，如何看待 18 世纪英国平民文化？',
'两次世界大战之间的日本陆军，他们如何走向战争？',
'艾滋病如何在美国被发现，又怎样展现人性的复杂？',
'卢梭研究经典，我们该如何理解卢梭的孤独？',
'社交媒体和数字技术的发展，如何改变传统人际关系？',
'如果爱情让人自身和自身保持同一，那它可能是什么？',
'130 幅城市复原图，如何重现古地中海文明？',
'从 1931 到 1945 年，日本人的思想发生了什么转变？',
'百年以来，什么是中国文人论政的报国情怀？']

简单爬虫练习：爬虫文章

简单爬虫练习：爬虫文章

------------------------------------------------------------------------------------------------------------------#

推荐阅读更多精彩内容