python爬虫，虎牙房间爬取（selenium）

coding=utf-8

“”"
author:lei
function: 虎牙直播爬取
“”"

import time
from selenium import webdriver

class HuYa(object):
def init(self):
self.url = “https://www.huya.com/l”
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(1)

    room_list = self.driver.find_elements_by_xpath("/html/body/div[2]/div/div/div[4]/ul/li")
    print(len(room_list))

    temp_list = []

    for room in room_list:
        temp = {}
        temp["title"] = room.find_element_by_xpath("./a[2]").text
        temp["url"] = room.find_element_by_xpath("./a[2]").get_attribute("href")
        temp["owner"] = room.find_element_by_xpath("./span[1]/span[1]/i").text
        temp["type"] = room.find_element_by_xpath("./span[1]/span[2]/a").text
        temp["num"] = room.find_element_by_xpath("./span[1]/span[3]/i[2]").text
        temp_list.append(temp)
    return temp_list

def save_data(self, temp_list):
    for temp in temp_list:
        print(temp)

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

    while True:
        temp_list = self.parse_data()

        self.save_data(temp_list)

        try:
            el_next = self.driver.find_element_by_xpath("//a[@class='laypage_next']")
            self.driver.execute_script("scrollTo(0, 100000)")
            el_next.click()
        except:
            print("结束！")
            break

if name == ‘main’:
huya = HuYa()
huya.run()