摘要

本文主要介绍了如何通过selenium使用Chormedriver进行用户登录并爬取数据，使用过程中需注意合理使用selenium.webdriver.support.expected_conditions
和selenium.webdriver.support.ui.WebDriverWait

（一）创建browser对象

chromedriver.exe的下载地址为：点此进行下载

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.common import by
from selenium.webdriver.common.action_chains import ActionChains
from lxml import etree

class ChromeCrawl(object):

    def __init__(self):
  
        chrome_options = webdriver.ChromeOptions()
        prefs = {"profile.managed_default_content_settings.images": 2}
        chrome_options.add_experimental_option("prefs", prefs)
        chrome_options.add_experimental_option('excludeSwitches', ['enable-automation']) 
        chrome_options.add_argument('--headless')
        chrome_options.add_argument('--no-sandbox')
        chrome_options.add_argument('--disable-gpu')
        
        self.browser = webdriver.Chrome(executable_path="./tools/chromedriver.exe", chrome_options=chrome_options)
        self.browser.set_page_load_timeout(60)
        self.browser.set_script_timeout(60)
        self.wait = WebDriverWait(self.browser, 60)

（二）用户登录

    def login(self):
        username = "*****"
        passwd = "******"

        self.browser.get('https:********login')
        self.browser.implicitly_wait(60)
        
        elem = self.browser.find_element_by_id("username")
        elem.send_keys(username)
        
        elem = self.browser.find_element_by_id("password")
        elem.send_keys(passwd)
        
        button = self.wait.until(expected_conditions.element_to_be_clickable((by.XPATH, '//*****')))# 根据自己的网页进行设置
        ActionChains(self.browser).click(button).perform()
    
        self.wait.until(expected_conditions.presence_of_element_located((by.CLASS_NAME, '******')))

（三）数据爬取

	def crawl(self):
        self.browser.get('https：******')
        self.wait.until(expected_conditions.presence_of_element_located((by.CLASS_NAME, '******')))
        html = etree.HTML(self.browser.page_source)
        tmp = html.xpath('//*****')