爬蟲2 urllib用法
阿新 • • 發佈:2019-01-08
from urllib import request,parse # 1. 解析資料 # 解析一條 # response = request.urlopen(url='http://httpbin.org/get?username={}'.format(parse.quote('哈哈'))) # print(response.read()) # # 解析字典 # data1 = { # 'username':'哈哈', # 'pass' : 23564 # } # res = parse.urlencode(data1) # print(res) # 2. 模擬請求頭# headers = { # 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6721.400 QQBrowser/10.2.2243.400' # } # req = request.Request( # url='http://img5.imgtn.bdimg.com/it/u=935292084,2640874667&fm=26&gp=0.jpg', # headers=headers# ) # response = request.urlopen(req) # print(response.read()) # 3. 傳送一個get請求 # response = request.urlopen(url='http://httpbin.org/get',timeout=0.1) # 傳送一個get請求 # response = request.urlopen(url='http://httpbin.org/get') # print(response.getcode()) #返回碼 # print(response.info()) #返回頭部資訊# print(response.read()) #返回內容 # response2 = request.urlopen(url='http://httpbin.org/post', # data = b'username=haha&password=12345'