Python网络数据采集-BeautifulSoup

from urllib.request import urlopen
html = urlopen("http://pythonscraping.com/pages/page1.html")

print(html.read())

from bs4 import BeautifulSoup
from urllib.request import urlopen
html = urlopen("http://pythonscraping.com/pages/page1.html")
bsobj = BeautifulSoup(html.read(),'html.parser')
print(bsobj)

#两种异常,1:网页在服务器上不存在,2:服务器不存在
from bs4 import BeautifulSoup
from urllib.request import urlopen
def getTitle(url):
    try:
        html = urlopen(url)
    except HTTPError as e:
        return None
        #异常,网页在服务器上不存在,不再执行 else 语句后面的代码
    try:
        bsobj = BeautifulSoup(html.read(),'html.parser')
        title = bsobj.body.h1
    except AttributeError as e:
        return None
    return title
title = getTitle("http://pythonscraping.com/pages/page1.html")
if title == None:
    print("Title is none")
else:
    print(title.text)