Python爬虫之Requests库的基本使用

import requests
response = requests.get('http://www.baidu.com/')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)

# 各种请求方式
import requests
requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')

# 基本GET请求
import requests
response = requests.get('http://httpbin.org/get')
print(response.text)

# 带参数GET请求
import requests
response = requests.get('http://httpbin.org/get?name=germey&age=22')
print(response.text)

import requests
data = {
    'name': 'germey',
    'age': 22
}
response = requests.get('http://httpbin.org/get', params = data)
print(response.text)

# 解析json
import requests
import json
response = requests.get('http://httpbin.org/get')
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(response.json()))

# 获取二进制数据
import requests
response = requests.get('http://github.com/favicon.ico')
print(type(response.text), type(response.content))
print(response.text)
print(response.content)

# 保存图片
import requests
response = requests.get('http://github.com/favicon.ico')
with open('1.ico', 'wb') as f:
    f.write(response.content)
    f.close()

# 添加headers 不添加的话会请求失败的
import requests
response = requests.get('http://www.zhihu.com/explore')
print(response.text)

import requests
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36'
}
response = requests.get('http://zhihu.com/explore', headers = headers)
print(response.text)

# 基本的POST请求
import requests
data = {'name': 'germey', 'age': 22}
response = requests.post('http://httpbin.org/post', data = data)
print(response.text)

import requests
data = {'name':'germey', 'age':22}
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36'
}
response = requests.post('http://httpbin.org/post', data = data, headers = headers)
print(response.json())

# response属性
import requests
response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)
print(type(response.headers), response.headers)
print(type(response.cookies), response.cookies)
print(type(response.url), response.url)
print(type(response.history), response.history)

# 文件上传
import requests
files = {'file':open('1.ico', 'rb')}
response = requests.post('http://httpbin.org/post', files = files)
print(response.text)

# 获取cookie
import requests
response = requests.get('http://www.baidu.com')
print(response.cookies)
for key, value in response.cookies.items():
    print(key + ' = ' + value)

# 会话维持 模拟登陆(第一个例子，相当于在两个不同的浏览器请求页面，所以获取不到cookies,所以要用第二个session对象)
import requests
requests.get('http://httpbin.org/cookies/set/number/123456789')
response = requests.get('http://httpbin.org/cookies')
print(response.text)

import requests
s = requests.session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

# 证书验证
import requests
response = requests.get('https://www.12306.cn')
print(response.status_code)

import requests
from requests.exceptions import ConnectTimeout, HTTPError, ReadTimeout, RequestException
from requests.auth import HTTPBasicAuth
import urllib3

# 证书验证
# 消除警告（下面的HTTPS页面的请求如果不进行验证就会报警告）
urllib3.disable_warnings()
# verify=False 请求HTTPS页面的时候不进行证书验证，默认为True
response = requests.get('https://www.12306.cn', verify=False)
print(response.status_code)

# 代理设置
proxies = {
    "http": "http://127.0.0.1:9743",
    "https": "https://127.0.0.1:9743",
}
response = requests.get("https://www.taobao.com", proxies = proxies)
print(response.status_code)

# 代理有用户名和密码的情况
proxies = {
    "http": "http://user:password@127.0.0.1:9743/",
}
response = requests.get("https://www.taobao.com", proxies = proxies)
print(response.status_code)

# socks代理
proxies = {
    "http": "socks5://127.0.0.1:9742",
    "https": "socks5://127.0.0.1:9742",
}
response = requests.get("https://www.taobao.com", proxies = proxies)
print(response.status_code)

# 超时设置
try:
    response = requests.get("http://httpbin.org/get", timeout=0.2)
    print(response.status_code)
except ConnectTimeout:
    print("timeout!")

# 认证设置 下面两种方法都可以
response = requests.get("http://120.27.34.24:9001", auth=HTTPBasicAuth("user", "123"))
print(response.status_code)

response = requests.get("http://120.27.34.24:9001", auth=("user", "123"))
print(response.status_code)

# 异常处理
try:
    response = requests.get("http://httpbin.org/get", timeout=0.2)
    print(response.status_code)
except ConnectTimeout:
    print("timeout!")
except RequestException:
    print("RequestException!")
except HTTPError:
    print("HttpError!")
except ReadTimeout:
    print("ReadTimeout")

import requests
response = requests.get("http://www.baidu.com")
print(response.cookies)
print("----------")
# 把cookie对象转化为字典
d = requests.utils.dict_from_cookiejar(response.cookies)
print(d)
print("----------")
# 把字典转化为cookie对象
print(requests.utils.cookiejar_from_dict(d))

# url解码
print(requests.utils.unquote("http://tieba.baidu.com/f?kw=%D2%D7%D3%EF%D1%D4&fr=ala0&tpl=5", encoding="gb18030"))
# url编码
print(requests.utils.quote("http://tieba.baidu.com/f?kw=%D2%D7%D3%EF%D1%D4&fr=ala0&tpl=5"))