[Python知识库]爬虫3--代理和selenium

代理和selenium

1.代理ip的使用

1.获取蘑菇代理中的代理ip

import requests


def get_ip():
    respond = requests.get('代理URL')
    if respond.text[0] == '{':
        print('提取ip失败')
     	return None
    return [x for x in respond.test.split('\n') if x]	# 如果不为空


# 使用代理ip
ips = get_ip()
ips = ['114.106.151.5:36293', '115.209.126.217:21170', '59.62.120.157:30400', '114.230.120.126:57022']
proxies = {'http': 'ips[0]', 'https': 'ip[1]'}
respond = requests.get('url', proxies=proxies)

2.使用代理的优化流程

import requests
import time


def get_ip():
    respond = requests.get('代理url')
    if respond.text[0] == '{':
        print('提取ip失败')
        time.sleep(5)
        li = get_ip()
    else:
        li = respond.text.split('\n')[0:4]
    return li

# ==============================


def get_ip():
    respond =  requests.get('代理url')
    while True:
        if repond.text[0] == '{':
            print('请求失败')
            time.sleep(5)
            continue
        else:
            return respond.text.split("\n")[0:4]

2.selenium的基本功能

from selenium.webdriver import Chrome

# 1.创建浏览器对象（如果是全局变量，程序结束浏览器不会关闭；局部变量会关闭
b = Chrome

# 2.输入网址
b.get('URL')

# 3.获取网页源代码
print(b.page_sourse)

# 4.关闭浏览器
b.close()

3.selenium的常规操作

from selenium.webdriver import Chrome
from selenium.webdriver.common.keys import Keys
import time

b = Chorme()
b.get('https://www.51job.com/')

# 获取输入标签(输入框)
search_input = b.find_element_by_id('kwdselectid')

# 在输入框中输入内容
search_input.send_keys('数据分析')

# 输入后按回车
search_input.send_keys(Keys.ENTER)
time.sleep(1)	# 休眠一秒

# 获取数据
info = b.page_source

# 获取下一页的标签
next = b.find_element_by_class_name('next')

# 点击对象
next.click()
time.sleep(1)
info = b.page_source

4.selenium常用配置

from selenium.webdriver import Chorme, ChormeOptions
import requests
import time

# 1. 创建谷歌浏览器设置对象
options = ChromeOptions()

# 2. 添加取消测试环境选项
options.add_experimental_option('excludeSwithes', ['enable-automation'])

# 3. 取消图片加载
options.add_experimental_option("prefs", {"profiles.managed_default_content_settings.image": 2})

# 4. 设置代理
option.add_argument(f'--proxy-server=http://{ips[0]})
                    
b = Chrome(options=options)
b.get('https://sec.douban.com/')    
info = b.page_source