python3.7簡單的爬蟲

#https://www.runoob.com/w3cnote/python-spider-intro.html
#Python 爬蟲介紹

 

import urllib.parse
import urllib.request
from http import cookiejar

 

url = "http://www.baidu.com"
response1 = urllib.request.urlopen(url)
print("第一種方法")
#獲取狀態碼，200表示成功
print(response1.getcode())
#獲取網頁內容的長度
print(str(response1.read()))
print(len(response1.read()))

print("第二種方法")
request = urllib.request.Request(url)
#模擬Mozilla瀏覽器進行爬蟲
request.add_header("user-agent","Mozilla/5.0")
response2 = urllib.request.urlopen(request)
print(response2.getcode())
print(len(response2.read()))

print("第三種方法")
cookie = cookiejar.CookieJar()
#加入urllib2處理cookie的能力#
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie))
urllib.request.install_opener(opener)
response3 = urllib.request.urlopen(url)
print(response3.getcode())
print(len(response3.read()))
print(cookie)


code： https://github.com/pascal19821003/python
path： python/study/tutorial/pachong/1.py