import requestsfrom bs4 import BeautifulSoup#将字符串转换为Python对象import pandas as pd
url = 'http://www.runoob.com/html/html-tutorial.html'r= requests.get(url)
html=r.text.encode(r.encoding).decode()
soup =BeautifulSoup(html,'lxml')#html放到beatifulsoup对象中l=[x.text for x in soup.findAll('h2')]#提取次标题中所有的文字df = pd.DataFrame(l,columns =[url])#将l变为DataFrame文件，列名为URLx=soup.findAll('a')[1]#查看第二个元素x.has_attr('href')#判断是都有href字符x.attrs['href']#获得超链接 attrs函数返回字典links = [i for i in soup.findAll('a')if i.has_attr('href')and i.attrs['href'][0:5]== '/html']#用if来做一个筛选relative_urls= set([i.attrs['href'] for i in links])
absolute_urls={'http://www.runoob.com'+i for i in relative_urls}
absolute_urls.discard(url)#删除当前所在的urlfor i in absolute_urls:
ri= requests.get(i)
soupi =BeautifulSoup(ri.text.encode(ri.encoding),'lxml')
li=[x.text for x in soupi.findAll('h2')]
dfi = pd.DataFrame(l,columns =[i])
df = df.join(dfi,how='outer')
df
