20220624 登录和代理ip

reques的登录反爬

python
from selenium.webdriver import Chrome, ChromeOptions

#1. 创建配置对象

options = ChromeOptions()

#1)取消测试环境

options.add_experimental_option(‘excludeSwitches’, [‘enable-automation’])

#2)取消图片加载

options.add_experimental_option(“prefs”, {“profile.managed_default_content_settings.images”: 2})

b = Chrome(options=options)

b.get(‘https://www.jd.com’)

input(‘end:’)
b.close()

selenium获取cookies

from selenium.webdriver import Chrome
from json import dumps

#1. 打开需要做自动登录的网站
b = Chrome()
b.get(‘https://www.51job.com/’)

#2. 提供足够长的时间让人工在这个页面中完成登录(登录后一定要保证b对应的窗口出现登录信息)
input(‘登录完成:’)

#3. 获取登录后的cookie信息保存到本地文件中(建议保存一个json)
cookies = b.get_cookies()

with open(‘files/taobao.json’, ‘w’, encoding=‘utf-8’) as f:
f.write(dumps(cookies))

b.close()

selenium使用cookies

python
from selenium.webdriver import Chrome
from json import loads

#1. 打开需要爬取的网站
b = Chrome()
b.get(‘https://www.taobao.com’)

#2.从cookie文件中获取cookie信息并且添加到浏览器对象中
with open(‘files/taobao.json’, encoding=‘utf-8’) as f:
cookies = loads(f.read())

for x in cookies:
b.add_cookie(x)

#3.重新打开网页
b.get(‘https://www.taobao.com’)

input(‘end:’)
b.close()

requests使用代理ip

python
import requests

headers = {
‘user-agent’: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36’
}

#创建代理对象
#proxies = {

‘https’: ‘http://183.165.224.25:4554’,

‘http’: ‘http://183.165.224.25:4554’

#}
proxies = {
‘https’: ‘183.165.224.25:4554’,
‘http’: ‘183.165.224.25:4554’
}
#发送请求的时候使用代理
response = requests.get(‘https://www.maoyan.com/’, headers=headers, proxies=proxies)
#解决乱码问题
response.encoding = ‘utf-8’
print(response.text)

代理ip的使用方法

python
import requests
import time
from bs4 import BeautifulSoup

def get_ip():
“”"
获取代理ip，如果获取失败过2秒再重新获取
:return: 获取到的ip地址
“”"
while True:
response = requests.get(‘http://d.jghttp.alicloudecs.com/getip?num=1&type=1&pro=510000&city=510600&yys=0&port=1&time=2&ts=0&ys=0&cs=0&lb=4&sb=0&pb=4&mr=1&regions=’)
result = response.text
if result[0] == ‘{’:
print(‘ip获取失败’)
time.sleep(2)
else:
return result

def get_net_data():
url = ‘https://www.maoyan.com/’
headers = {
‘user-agent’: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36’
}

#使用代理ip发送请求，如果代理失败，重新获取新的ip重新再发送请求
while True:
    ip = get_ip()
    print(ip)
    proxy = {
        'https': ip
    }
    response = requests.get(url, headers=headers, proxies=proxy)
    response.encoding = 'utf-8'
    print(response.text)

    soup = BeautifulSoup(response.text, 'lxml')
    movies_div = soup.select('.movie-list .movie-item')
    if len(movies_div) == 0:
        continue
    else:
        print('爬虫成功!做后续的解析操作')
        break

if name == ‘main’:
get_net_data()