关于反爬虫的一些简单总结

headers = {
'Host': "bj.lianjia.com",
'Accept': "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
'Accept-Encoding': "gzip, deflate, sdch",
'Accept-Language': "zh-CN,zh;q=0.8",
'User-Agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36",
'Connection': "keep-alive",
}
p = requests.get(url, headers=headers)
print(p.content.decode('utf-8'))

from selenium import webdriver
from selenium.webdriver.common.keys import Keys #
from selenium.webdriver.support.ui import WebDriverWait # WebDriverWait的作用是等待某个条件的满足之后再往后运行
from selenium.webdriver import ActionChains
import time
import sys
driver = webdriver.PhantomJS(executable_path='C:\PyCharm 2016.2.3\phantomjs\phantomjs.exe') # 构造网页驱动

driver.get('https://www.zhihu.com/#signin')  # 打开网页
driver.find_element_by_xpath('//input[@name="password"]').send_keys('your_password')
driver.find_element_by_xpath('//input[@name="account"]').send_keys('your_account')
driver.get_screenshot_as_file('zhihu.jpg')     # 截取当前页面的图片
input_solution = input('请输入验证码 :')
driver.find_element_by_xpath('//input[@name="captcha"]').send_keys(input_solution)
time.sleep(2)

driver.find_element_by_xpath('//form[@class="zu-side-login-box"]').submit() # 表单的提交 表单的提交，即可以选择登录按钮然后使用click方法，也可以选择表单然后使用submit方法
sreach_widonw = driver.current_window_handle  # 用来定位当前页面
# driver.find_element_by_xpath('//button[@class="sign-button submit"]').click()
try:
dr = WebDriverWait(driver,5)
# dr.until(lambda the_driver: the_driver.find_element_by_xpath('//a[@class="zu-side-login-box"]').is_displayed())
if driver.find_element_by_xpath('//*[@id="zh-top-link-home"]'):
print('登录成功')
except:
print('登录失败')
driver.save_screenshot('screen_shoot.jpg')  #截取当前页面的图片
sys.exit(0)
driver.quit() #退出驱动

import requests
proxies = { "http": "http://10.10.1.10:3128",
"https": "http://10.10.1.10:1080",}
p = request.get("http://www.baidu.com", proxies = proxies)
print(p.content.decode('utf-8'))

user_agent ='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0'
headers = {'User-Agent':user_agent}
proxy = {'http':'http://10.10.1.10:1080',}
proxy_handler = urllib.request.ProxyHandler(proxy)
opener = urllib.request.build_opener(proxy_handler)
urllib.request.install_opener(opener)
url = "https://www.baidu.com/"
req = urllib.request.Request(url=url,headers=headers)
res = urllib.request.urlopen(req)
print(res.read().decode('utf-8')) # 打印网页内容

driver = webdriver.PhantomJS(executable_path='C:\PyCharm 2016.2.3\phantomjs\phantomjs.exe') # 构造网页驱动
driver.get('https://www.zhihu.com/') 
print(driver.page_source) # 打印网页内容