python用Selenium爬取携程网机票信息

一、问题说明

1、selenium库是爬虫过程中比较讨巧的一个第三方库，它能够跳过js、ajax等交互，上手比较容易。

2、基础代码是根据其他博主参考而来，但携程网站不断变化，除ID等不变的信息外，其余都已发生变化，因此，仔细对比之后，改进并编写了以下代码，发布于2021年10月19日。

3、如果出现报错，请尝试修改下面代码中 time.sleep()函数参数。

4、要爬取自己想要的数据，只需修改出发地和到达地以及出发时间，另外注意修改浏览器驱动，本人用的是MicroSoft Edge，驱动到对应的网站下载，下载后要更名驱动并修改 driver_path参数。

4、目前只是一个基础版本，后续可能会发布更新版，如加入直飞、中转、经停等个性化数据爬取。

5、代码只供学习参考，请勿商用！

二、代码

# -*- coding:utf-8 -*-
# 利用selenium爬取携程
# Author: KingStar
import time
from selenium import webdriver
from bs4 import BeautifulSoup

def page_select_function(driver_path):
    driver = webdriver.Edge(executable_path=driver_path)
    driver.get('https://www.ctrip.com/')
    time.sleep(1)
    # 窗口最大化
    driver.maximize_window()
    # 从首页选择进入机票页面
    input_tag_slect = driver.find_element_by_class_name('s_tab_nocurrent')
    input_tag_slect.click()
    time.sleep(1)
    # 选择日期
    input_tag_time = driver.find_element_by_id('FD_StartDate')
    input_tag_time.send_keys('2021-10-20')
    time.sleep(1)
    # 选择出发城市
    input_tag_depart_city = driver.find_element_by_id('FD_StartCity')
    input_tag_depart_city.send_keys('厦门')
    time.sleep(1)
    # 选择到达城市
    input_tag_arrive_city = driver.find_element_by_id('FD_DestCity')
    input_tag_arrive_city.send_keys('兰州')
    time.sleep(1)
    # 开始搜索
    input_tag_search = driver.find_element_by_id('FD_StartSearch')
    # driver.find_element(By.CSS_SELECTOR, "#submit").send_keys(Keys.ENTER)
    driver.execute_script("arguments[0].click();", input_tag_search)
    # input_tag_search.click()
    time.sleep(3)
    # 关闭紧急公告提示
    tag_close = driver.find_element_by_class_name('close-icon')
    tag_close.click()
    time.sleep(1)
    # 只选择经停
    tag_select = driver.find_element_by_class_name('auto_cursor')
    tag_select.click()
    time.sleep(2)
    driver.find_element_by_xpath('//*[@id="domestic_filter_group_trans_and_train__trans_count"]/li[2]/span').click()
    driver.find_element_by_class_name('flight-part').click()
    time.sleep(1)
    '''
    # 只选择直飞
    direct_flight_tag_click = driver.find_element_by_class_name('form-label')
    direct_flight_tag_click.click()
    time.sleep(2)
    '''
    for i in range(1):
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(1)
    return driver

def data_acquistion(driver):
    source = driver.page_source
    bs = BeautifulSoup(source, 'html.parser')
    divs = bs.find_all('div', class_='flight-item domestic')
    return divs

def data_treating(divs):
    for div in divs:
        try:
            airlineName = div.find('div', class_='airline-name').get_text()
            flightNumber = div.find_all('span', class_='plane-No')[0].get_text()
            # craftTypeName = div.find('span', class_='direction_black_border low_text').string
            departureTime = div.find('div', class_='depart-box').find('div', class_='time').string
            arrivalTime = div.find('div', class_='arrive-box').find('div', class_='time').get_text()
            lowestPrice = div.find('span', class_='price').get_text()
            print(airlineName, '\t', flightNumber, '\t', departureTime, '\t', arrivalTime, '\t', lowestPrice)
            time.sleep(1)
        except:
            print(无该信息)

def main():
    driver_path = r'C:\MicrosoftWebDriver.exe'
    driver = page_select_function(driver_path)
    divs = data_acquistion(driver)
    data_treating(divs)
    driver.close()

if __name__ == '__main__':
    main()