python爬虫，斗鱼房间爬取（selenium）

coding=utf-8

“”"
author:lei
function:斗鱼网站的爬取
“”"

import time
from selenium import webdriver

class DouYu(object):

def __init__(self):
    self.url = "https://www.douyu.com/directory/all"
    options = webdriver.ChromeOptions()
    options.binary_location = r"D:\文件2\Google\Chrome\Application\chrome.exe"
    self.driver = webdriver.Chrome(r"D:\文件\软件\chromedriver_win32\chromedriver.exe", options=options)

def parse_data(self):
    time.sleep(2)
    room_list = self.driver.find_elements_by_xpath("//*[@id='listAll']/section[2]/div[2]/ul/li/div")
    print(len(room_list))

    data_list = []

    # 遍历房间列表，从每一个房间节点中获取数据
    for room in room_list:
        temp = {}

        temp["title"] = room.find_element_by_xpath("./a[1]/div[2]/div[1]/h3").text
        temp["type"] = room.find_element_by_xpath("./a[1]/div[2]/div[1]/span").text
        temp["owner"] = room.find_element_by_xpath("./a[1]/div[2]/div[2]/h2").text
        temp["num"] = room.find_element_by_xpath("./a[1]/div[2]/div[2]/span").text
        temp["img"] = room.find_element_by_xpath("./a/div[1]/div[1]/img").get_attribute("src")
        data_list.append(temp)

    return data_list

def save_data(self, data_list):
    for data in data_list:
        print(data)

def run(self):
    # url
    # driver
    # get
    self.driver.get(self.url)

    while True:
        # parse
        data_list = self.parse_data()

        # save
        self.save_data(data_list)

        # next
        try:
            el_next = self.driver.find_element_by_xpath("//li[@class=' dy-Pagination-next']/span")

            self.driver.execute_script("scrollTo(0, 100000)")

            el_next.click()
        except:
            break

if name == ‘main’:
douyu = DouYu()
douyu.run()