xpath练习

DouyuSpider

今天学习了xpath方法， 拿斗鱼主播的房间信息做一个练习，有不足之处希望各位大佬帮忙斧正。

#encoding=utf-8

from selenium import webdriver
import time, json

class DouyuSpider:

    def __init__(self):
        self.start_url = "https://www.douyu.com/directory/all"
        self.driver    = webdriver.Chrome() # 实例化一个浏览器
        self.page_num  = 0                  # 页数

    def get_contnet_list(self):
        # 先对li标签进行分组
        li_list = self.driver.find_elements_by_xpath("//div[@class='layout-Module-container layout-Cover ListContent']//ul[@class='layout-Cover-list']/li")
        content_list = []
        # 再对每一组的li进行数据提取
        for li in li_list:
            item = {}
            item["room_img"] = li.find_element_by_xpath(".//div[@class='DyListCover-imgWrap']//img").get_attribute("src")
            item["room_title"]= li.find_element_by_xpath(".//h3[@class='DyListCover-intro']").text
            item["room_cate"] = li.find_element_by_xpath(".//span[@class='DyListCover-zone']").text
            item["anchor_name"]=li.find_element_by_xpath(".//h2[@class='DyListCover-user']").text
            item["room_people"]=li.find_element_by_xpath(".//span[@class='DyListCover-hot']").text
            content_list.append(item)
        # 获取下一页的元素
        next_page = self.driver.find_elements_by_xpath("//span[text()='下一页']")
        next_page = next_page[0] if len(next_page) > 0 else None    # 当执行到最后一页时, next_page为 None, 整个程序结束
     	return content_list, next_page

    def save_content_list(self, content_list):
        with open("douyu.txt", "a", encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content, ensure_ascii=False))
                f.write("\n\n")
        self.page_num += 1
        print("第{}页完毕".format(self.page_num))

    # 实现主要逻辑
    def run(self):
        # 1.strat_url
        # 2.发送请求
        self.driver.get(self.start_url)
        # 3.提取数据
        content_list, next_page = self.get_contnet_list()
        # 4.保存数据
        self.save_content_list(content_list)
        # 5.点击下一页元素
        while next_page is not None:
            next_page.click()
            time.sleep(2)             # 防止因执行速度过快，而导致浏览器没有接收到服务端发出的信息
            content_list, next_page = self.get_contnet_list()
            self.save_content_list(content_list)

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