python +headless+chrome 模拟搜索百度关键词

【实例截图】

【核心代码】

#!/usr/bin/env python
# -*- coding:utf-8 -*-

from selenium import webdriver
from selenium.webdriver.common.proxy import Proxy, ProxyType


options = webdriver.ChromeOptions()

# tell selenium to use the dev channel version of chrome
# NOTE: only do this if you have a good reason to
# options.binary_location = '/usr/bin/google-chrome-unstable'  # path to google Chrome bin

options.add_argument('headless')

# set the window size
options.add_argument('window-size=1200x600')

# with proxy
proxy_url = 'ip:port'
proxy = Proxy({
    'proxyType': ProxyType.MANUAL,
    'httpProxy': proxy_url,
    'sslProxy': proxy_url  # 需要信任代理服务器CA证书
})

desired_capabilities = options.to_capabilities()
proxy.add_to_capabilities(desired_capabilities)

# initialize the driver
# driver = webdriver.Chrome(chrome_options=options)
driver = webdriver.Chrome(chrome_options=options, desired_capabilities=desired_capabilities)


driver.get('https://www.baidu.com')

# wait up to 10 seconds for the elements to become available
driver.implicitly_wait(10)
driver.get_screenshot_as_file('baidu_index.png')

# use css selectors to grab the search inputs
text = driver.find_element_by_css_selector('#kw')
search = driver.find_element_by_css_selector('#su')

text.send_keys('headless chrome')

driver.get_screenshot_as_file('baidu_main-page.png')


# search
search.click()
driver.get_screenshot_as_file('search-result.png')

results = driver.find_elements_by_xpath('//div[@class="result c-container "]')

for result in results:
    res = result.find_element_by_css_selector('a')
    title = res.text
    link = res.get_attribute('href')
    print ('Title: %s \nLink: %s\n' % (title, link))