封装简单爬取的函数

from urllib import request,parse
from urllib.error import HTTPError,URLError
def get(url, headers=None):
return urlrequests(url, headers=headers)

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

def urlrequests(url, form=None, headers=None):
user_agent = ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36’
# 如果用户需要自行传入headers, 则覆盖之前的headers
if headers == None:
headers = {
‘User-Agent’: user_agent
}
html_bytes = b”
try:
if form:
# POST
# 2.1 转换成str
form_str = parse.urlencode(form, encoding=’utf-8’)
#print(form_str)
# 2.2 转换成bytes
form_bytes = form_str.encode(‘utf-8’)
req = request.Request(url, data=form_bytes, headers=headers)
else:
# GET
req = request.Request(url, headers=headers)
response = request.urlopen(req)
html_bytes = response.read()
except HTTPError as e:
print(e)
except URLError as e:
print(e)

return html_bytes

if name == ‘main‘:

url = 'http://www.baidu.com'
html_byte = get(url)
print(html_byte)