python爬蟲利用selenium實現自動翻頁爬取某魚數據的思路詳解

from selenium import webdriver
import time
import re

class Douyu(object):

  def __init__(self):
    # 開始時的url
    self.start_url = "https://www.douyu.com/directory/all"
    # 實例化一個Chrome對象
    self.driver = webdriver.Chrome()
    # 用來寫csv文件的標題
    self.start_csv = True

  def __del__(self):
    self.driver.quit()

  def get_content(self):
    # 先讓程序兩秒,保證頁面所有內容都可以加載出來
    time.sleep(2)
    item = {}
    # 獲取進入下一頁的標簽
    next_page = self.driver.find_element_by_xpath("//span[text()='下一頁']/..")
    # 獲取用於判斷是否是最後一頁的屬性
    is_next_url = next_page.get_attribute("aria-disabled")
    # 獲取存儲信息的所有li標簽的列表
    li_list = self.driver.find_elements_by_xpath("//ul[@class='layout-Cover-list']//li")
    
    # 提取需要的數據
    for li in li_list:
      
      item["user-id"] = li.find_element_by_xpath(".//div[@class='DyListCover-userName']").text
      item["img"] = li.find_element_by_xpath(".//div[@class='DyListCover-imgWrap']//img").get_attribute("src")
      item['class-name'] = li.find_element_by_xpath(".//span[@class='DyListCover-zone']").text
      item["click-hot"] = li.find_element_by_xpath(".//span[@class='DyListCover-hot']").text
      item["click-hot"] = re.sub(r'\n','',item['click-hot'])
      
      # 保存數據
      self.save_csv(item)
    
    # 返回是否有下一頁和下一頁的點擊事件的標簽,
    return next_page,is_next_url

  def save_csv(self,item):
    # 將提取存放到csv文件中的內容連接為csv格式文件
    str = ','.join([i for i in item.values()])

    with open('./douyu.csv','a',encoding='utf-8') as f:
      if self.start_csv:
        f.write("用戶id,image,所屬類,點擊熱度\n")
        self.start_csv = False
      # 將字符串寫入csv文件
      f.write(str)
      f.write('\n')
    print("save success")

  def run(self):
    # 啟動chrome並定位到相應頁面
    self.driver.get(self.start_url)

    while True:
      # 開始提取數據,並獲取下一頁的元素
      next_page,is_next = self.get_content()
      if is_next!='false':
        break
      # 點擊下一頁
      next_page.click()

if __name__=='__main__':
  douyu_spider = Douyu()
  douyu_spider.run()