21天打造分布式爬蟲-requests庫（二）

2.1.get請求

簡單使用

import requests

response = requests.get("https://www.baidu.com/")
#text返回的是unicode的字符串，可能會出現亂碼情況
# print(response.text)

#content返回的是字節，需要解碼
print(response.content.decode('utf-8'))


# print(response.url)             #https://www.baidu.com/
# print(response.status_code)     #200
# print(response.encoding)        #ISO-8859-1

添加headers和params

import requests

params = {
    'wd':'python'
}
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36'
}

response = requests.get("https://www.baidu.com/s",params=params,headers=headers)

#content返回的是字節，需要解碼
with open('baidu.html','w',encoding='utf-8') as f:
    f.write(response.content.decode('utf-8'))

2.2.POST請求

 爬去拉鈎網職位信息

import requests

url = "https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false"

data = {
    'first':'true',
    'pn':1,
    'kd':'python'
}

headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36",
    "Referer":"https://www.lagou.com/jobs/list_python?city=%E5%8C%97%E4%BA%AC&cl=false&fromSearch=true&labelWords=&suginput="
}

response = requests.post(url,data=data,headers=headers)
# print(response.text)
print(type(response.text))       #<class 'str'>
print(type(response.json()))     #<class 'dict'>

print(response.json())           #獲取為字典的形式

 2.3.使用代理

import requests

proxy = {'http':'115.210.31.236.55:9000'}

response = requests.get("https://www.baidu.com/",proxies=proxy)

print(response.content.decode('utf-8'))

2.4.session登錄

# _*_ coding:utf-8 _*_

import requests

# 1. 創建session對象，可以保存Cookie值
ssion = requests.session()

# 2. 處理 headers
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}

# 3. 需要登錄的用戶名和密碼
data = {"email":"158xxxxxxxx", "password":"pythonxxxxxxx"}

# 4. 發送附帶用戶名和密碼的請求，並獲取登錄后的Cookie值，保存在ssion里
ssion.post("http://www.renren.com/PLogin.do", data = data)

# 5. ssion包含用戶登錄后的Cookie值，可以直接訪問那些登錄后才可以訪問的頁面
response = ssion.get("http://zhibo.renren.com/news/108")

# 6. 打印響應內容
print(response.text)