Python爬虫入门的封装

from urllib import request,parse
from urllib.error import HTTPError,URLError

def get(url,headers=None):
#headers必须赋予变量否则属于位置参数会在调用函数中被当成form
return urlrequests(url,headers=headers)

def post(url,form,headers=None):
return urlrequests(url,form,headers=headers)

def urlrequests(url,form=None,headers=None):
if headers == None:
headers = {
‘User-Agent’:’Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36’
}
html_bytes = b”
try:
if form:
#转换成str
form_str = parse.urlencode(form)
#转换成bytes
form_bytes = form_str.encode(‘utf-8’)
req = request.Request(url,data=form_bytes,headers=headers)
else:
req = request.Request(url,headers=headers)
response = request.urlopen(req)
html_bytes = response.read()
except HTTPError as a:
print(a)
except URLError as a:
print(a)
return html_bytes
if name==’main‘:
#根据自身需要爬去的网站改变路由和请求方法，再改变下编码
url = ‘http://www.baidu.com’
html = get(url)
print(html)