python使用selenium實現(xiàn)爬蟲知乎

from selenium import webdriver # 從selenium導(dǎo)入webdriver
from selenium.webdriver.common.by import By # 內(nèi)置定位器策略集
from selenium.webdriver.support.wait import WebDriverWait # 用于實例化一個Driver的顯式等待
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import time

option = webdriver.ChromeOptions()
option.add_argument("headless")
driver = webdriver.Chrome() # chrome_options=option 這個參數(shù)設(shè)置之后可以隱藏瀏覽器
driver.get('https://www.zhihu.com/question/22110581') #修改這里的地址
file = open("./messages.txt", "w")


def waitFun():
  js = """
  let equalNum = 0;
  window.checkBottom = false;
  window.height = 0;
  window.intervalId = setInterval(()=>{
    let currentHeight = document.body.scrollHeight;
    if(currentHeight === window.height){
      equalNum++;
      if(equalNum === 2){
        clearInterval(window.intervalId);
        window.checkBottom = true;
      }
    }else{
      window.height = currentHeight;
      window.scrollTo(0,window.height);
      window.scrollTo(0,window.height-1000);
    }
  },1500)"""
  # 這個暫停一下是因為要等待頁面將下面的內(nèi)容加載出,這個 1500 可以根據(jù)自己的網(wǎng)絡(luò)快慢進行適當?shù)恼{(diào)節(jié)
  # 這里需要往上移動一下，因為不往上移動一下發(fā)現(xiàn)不會加載。
  driver.execute_script(js)

# selenium 可以獲取 瀏覽器中 js 的變量。調(diào)用的js return
def getHeight(nice):
  # 這里獲取 js 中的 checkBottom 變量，作為到底部時進行停止。
  js = """
  return window.checkBottom;
  """
  return driver.execute_script(js)


try:
  # 先觸發(fā)登陸彈窗。
  WebDriverWait(driver, 40, 1).until(EC.presence_of_all_elements_located(
    (By.CLASS_NAME, 'Modal-backdrop')), waitFun())

  # 點擊空白關(guān)閉登陸窗口
  ActionChains(driver).move_by_offset(200, 100).click().perform()
  # 當滾動到底部時
  WebDriverWait(driver, 40, 3).until(getHeight, waitFun())
  # 獲取回答
  answerElementArr = driver.find_elements_by_css_selector('.RichContent-inner')
  for answer in answerElementArr:
    file.write('==================================================================================')
    file.write('\n')
    file.write(answer.text)
    file.write('\n')
  print('爬取成功 '+ str(len(answerElementArr)) +' 條，存入到 message.txt 文件內(nèi)')
finally:
  driver.close()  #close the driver