Python爬虫之requests库基本介绍

pip install requests

import requests

response = requests.get('http://www.baidu.com')
print(response.status_code)  # 打印状态码
print(response.url)          # 打印请求url
print(response.headers)      # 打印头信息
print(response.cookies)      # 打印cookie信息
print(response.text)  #以文本形式打印网页源码
print(response.content) #以字节流形式打印
print(response.content.decode("utf-8")) #解决了通过response.text直接返回显示乱码的问题
response.encoding="utf-8" #避免乱码的问题发生

import requests

requests.get('http://httpbin.org/get')
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')

import requests

response = requests.get('http://httpbin.org/get')
print(response.text)

import requests

response = requests.get(http://httpbin.org/get?name=gemey&age=22)
print(response.text)

import requests

data = {
    'name': 'tom',
    'age': 20
}
response = requests.get('http://httpbin.org/get', params=data)
print(response.text)

import requests

response = requests.get('http://httpbin.org/get')
print(response.text)
print(response.JSON())  #response.json()方法同json.loads(response.text)
print(type(response.json()))

import requests

response = requests.get('/file/imgs/upload/202211/13/c11ssneilyl.jpg')
b = response.content
with open('F://fengjing.jpg','wb') as f:
    f.write(b)

import requests
heads = {}
heads['User-Agent'] = 'Mozilla/5.0 ' \
                          '(Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWEBKit/534.50 ' \
                          '(Khtml, like Gecko) Version/5.1 Safari/534.50'
 response = requests.get('http://www.baidu.com',headers=headers)

import requests
import re

def get_html(url):
    proxy = {
        'http': '120.25.253.234:812',
        'https': '163.125.222.244:8123'
    }
    heads = {}
    heads['User-Agent'] = 'Mozilla/5.0 (windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
    req = requests.get(url, headers=heads,proxies=proxy)
    html = req.text
    return html

def get_ipport(html):
    regex = r'<td data-title="IP">(.+)</td>'
    iplist = re.findall(regex, html)
    regex2 = '<td data-title="PORT">(.+)</td>'
    portlist = re.findall(regex2, html)
    regex3 = r'<td data-title="类型">(.+)</td>'
    typelist = re.findall(regex3, html)
    sumray = []
    for i in iplist:
        for p in portlist:
            for t in typelist:
                pass
            pass
        a = t+','+i + ':' + p
        sumray.append(a)
    print('高匿代理')
    print(sumray)


if __name__ == '__main__':
    url = 'http://www.kuaidaili.com/free/'
    get_ipport(get_html(url))

import requests

data = {'name':'tom','age':'22'}

response = requests.post('http://httpbin.org/post', data=data)

import requests

response = requests.get('http://www.baidu.com')
print(response.cookies)
print(type(response.cookies))
for k,v in response.cookies.items():
    print(k+':'+v)

import requests

session = requests.Session()
session.get('http://httpbin.org/cookies/set/number/12345')
response = session.get('http://httpbin.org/cookies')
print(response.text)

import requests
from requests.packages import urllib3

urllib3.disable_warnings()  #从urllib3中消除警告
response = requests.get('https://www.12306.cn',verify=False)  #证书验证设为FALSE
print(response.status_code)

import requests
from requests.exceptions import ReadTimeout

try:
    res = requests.get('http://httpbin.org', timeout=0.1)
    print(res.status_code)
except ReadTimeout:
    print(timeout)

import requests
from requests.exceptions import ReadTimeout,HTTPError,RequestException

try:
    response = requests.get('http://www.baidu.com',timeout=0.5)
    print(response.status_code)
except ReadTimeout:
    print('timeout')
except HTTPError:
    print('httperror')
except RequestException:
    print('reqerror')