经典爬虫学习（四）-selsenium实现斗鱼直播房间信息爬取

本案例中通过两种不同的selenium作用实现了对斗鱼直播平台的房间信息进行多页爬取。

• selenium实现信息爬取以及页面跳转功能
• selenium实现页面跳转功能，lxml解析库实现数据爬取功能

1.selenium实现信息爬取以及页面跳转功能

# coding=utf-8
from selenium import  webdriver
import time

class DouyuSpider:
    def __init__(self):
        self.start_url = "https://www.douyu.com/directory/all"
        self.driver = webdriver.Chrome()

    def get_content_list(self):
        li_list = self.driver.find_elements_by_xpath("//ul[@class='layout-Cover-list']/li")

        content_list = []
        for li in li_list:
            item = {}
            item["room_img"]=li.find_element_by_xpath(".//div[contains(@class,'LazyLoad')]/img").get_attribute("src")
            item["room_title"] = li.find_element_by_xpath(".//h3").get_attribute("title")
            item["room_cate"] = li.find_element_by_xpath(".//span[contains(@class,'DyListCover-zone')]").text
            item["anchor_name"] = li.find_element_by_xpath(".//h2[@class='DyListCover-user']").text
            item["watch_num"] = li.find_element_by_xpath(".//span[@class='DyListCover-hot']").text
            print(item)
            content_list.append(item)



        # 获取下一页的元素
        next_url = self.driver.find_elements_by_xpath("//span[@class='dy-Pagination-item-custom']")
        next_url = next_url[1] if self.driver.find_elements_by_xpath("//span[@class='dy-Pagination-item-custom']/..")[1].get_attribute("aria-disabled") == "false" else None
        return content_list,next_url

    def save_content_list(self,content_list):
        pass


    def run(self):#实现主要逻辑
        #1.start_url
        #2.发送请求，获取响应
        self.driver.get(self.start_url)
        #3.提取数据，提取下一页的元素
        content_list,next_url = self.get_content_list()
        #4.保存数据
        self.save_content_list(content_list)
        #5.点击下一页元素，循环
        while next_url is not None:
            next_url.click() #点击下一页
            print("点击成功")
            time.sleep(3) #会立刻提取数据，所以需要等待
            content_list,next_url = self.get_content_list()
            self.save_content_list(content_list)


if __name__ == '__main__':
    douyu = DouyuSpider()
    douyu.run()

• 数据保存部分请读者自行编写，可以选择任意输出格式

2.selenium实现页面跳转功能，lxml解析库实现数据爬取功能

# coding=utf-8
from selenium import  webdriver
import time
from lxml import etree

class DouyuSpider:
    def __init__(self):
        self.start_url = "https://www.douyu.com/directory/all"
        self.driver = webdriver.Chrome()

    def get_content_list(self):
        html_data = self.driver.page_source
        data = etree.HTML(html_data)
        li_list = data.xpath("//ul[@class='layout-Cover-list']/li")

        content_list = []
        for li in li_list:
            item = {}
            item["room_img"]=li.xpath(".//div[contains(@class,'LazyLoad')]/img/@src")
            item["room_title"] = li.xpath(".//h3/@title")
            item["room_cate"] = li.xpath(".//span[contains(@class,'DyListCover-zone')]/text()")
            item["anchor_name"] = li.xpath(".//h2[@class='DyListCover-user']/text()")
            item["watch_num"] = li.xpath(".//span[@class='DyListCover-hot']/text()")
            print(item)
            content_list.append(item)



        # 获取下一页的元素
        next_url = self.driver.find_elements_by_xpath("//span[@class='dy-Pagination-item-custom']")
        next_url = next_url[1] if self.driver.find_elements_by_xpath("//span[@class='dy-Pagination-item-custom']/..")[1].get_attribute("aria-disabled") == "false" else None
        return content_list,next_url

    def save_content_list(self,content_list):
        pass


    def run(self):#实现主要逻辑
        #1.start_url
        #2.发送请求，获取响应
        self.driver.get(self.start_url)
        #3.提取数据，提取下一页的元素
        content_list,next_url = self.get_content_list()
        #4.保存数据
        self.save_content_list(content_list)
        #5.点击下一页元素，循环
        while next_url is not None:
            next_url.click() #点击下一页
            print("点击成功")
            time.sleep(3) #会立刻提取数据，所以需要等待
            content_list,next_url = self.get_content_list()
            self.save_content_list(content_list)


if __name__ == '__main__':
    douyu = DouyuSpider()
    douyu.run()