爬虫学习之第一次获取网页内容及BeautifulSoup处理

 from urllib.request import urlopen
 from urllib.request import HTTPError
 from bs4 import BeautifulSoup

 def getTag(url,tager):
     try:
         html = urlopen(url)
     except HTTPError as e:
         return None
     try:
         bsObj = BeautifulSoup(html.read(),"html.parser")
         print(tager)
         title = bsObj(tager)
     except AttributeError as e:
         return None
     return title

 title = getTag("http://www.pythonscraping.com/pages/page1.html",'title')
 if title is None:
     print("Title could not be found")
 else:
     print(title)

实例二、只获取单个标签

 from urllib.request import urlopen
 from urllib.request import HTTPError
 from bs4 import BeautifulSoup

 def getTitle(url):
     try:
         html = urlopen(url)
     except HTTPError as e:
         return None
     try:
         bsObj = BeautifulSoup(html.read(),"html.parser")
         title = bsObj.title
     except AttributeError as e:
         return None
     return title

 title = getTitle("http://www.pythonscraping.com/pages/page1.html")
 if title is None:
     print("Title could not be found")
 else:
     print(title)