[Python知识库]python爬取某海鲜直播标题，热度等

用selenium库
先导包
我这已经导过了，只要导完不报错就行

代码附上

# 导包
from selenium import webdriver
import time
# 爬取海鲜 标题  主播类型  主播名  主播热度  链接
class Douyu(object):
    def __init__(self):
        self.url = 'https://www.douyu.com/directory/all'
        self.driver = webdriver.Chrome()
    def paqu(self):
        # 等待1秒
        time.sleep(1)
        # 获取标签
        el_list = self.driver.find_elements_by_xpath('//*[@id="listAll"]/section[2]/div[2]/ul/li/div')
        # 创建列表保存所有爬取的数据
        list_duyu =[]
        # 遍历标签，通过xpath获取标签并的到文本内容
        for el in el_list:
            temp ={}
            temp['title'] = el.find_element_by_xpath('./a/div[2]/div[1]/h3').text
            temp['title'] = temp['title'].encode("gbk", "ignore").decode("gbk")
            temp['type'] = el.find_element_by_xpath('./a/div[2]/div[1]/span').text
            temp['主播'] = el.find_element_by_xpath('./a/div[2]/div[2]/h2').text
            temp['热度'] = el.find_element_by_xpath('./a/div[2]/div[2]/span').text
            # temp['链接'] = el.find_element_by_xpath('//*[@class="LazyLoad is-visible DyImg DyListCover-pic"]/img | //*[@class="LazyLoad is-visible DyImg DyListCover-pic"]/picture/img').text
            # temp['链接'] = el.find_element_by_xpath('./a/div[1]/div[1]/img |  //*[@id="listAll"]/section[2]/div[2]/ul/li/div/a/div[1]/div[1]//picture/img').get_attribute("src")
            temp['链接'] = el.find_element_by_xpath('./a').get_attribute("href")
            list_duyu.append(temp)
        return list_duyu
    def tiqu(self,data):
        for da in data:
            print(da)
    def run(self):
        # url
        #driver
        #paqu
        self.driver.get(self.url)
        while True:
            data = self.paqu()
            #tiqu
            self.tiqu(data)
            #fanyi
            try:
                el_next = self.driver.find_element_by_xpath('//*[@class=" dy-Pagination-next"]/span')
                print(el_next)
                self.driver.execute_script('window.scrollTo(0,100000)')
                el_next.click()
            except:
                break
#                 主入口
if __name__ == '__main__':
        douyu = Douyu()
        douyu.run()