开启人生第一次爬虫（煎蛋网）

python+selenium爬取煎蛋网图片
网址：http://jandan.net/ooxx

#coding:utf-8
import requests
from selenium import webdriver
from selenium.webdriver.common.by import By
import os.path

class getImg():
    def __init__(self):
        self.url = "http://jandan.net/ooxx"
        self.driver = webdriver.Chrome()

    def list_img(self):
        imgs = self.driver.find_elements(By.XPATH, '//div[@id="comments"]/ol/li')
        imgList = []
        for img in imgs:
            if img.get_attribute("class") != 'row':
                png = img.find_element_by_xpath('.//div[@class="text"]/p/img').get_attribute("src")
                imgList.append(png)
        return imgList

    def save_img(self, list):
        file_name = './煎蛋网'
        if os.path.isdir(file_name) is not True:
            os.mkdir(file_name)

        for img in list:
            print(img)
            data = requests.get(img).content
            with open(file_name+'/'+img[-10:], 'wb') as f:
                f.write(data)

    def run(self):
        self.driver.get(self.url)
        for i in range(0,5):
            print("============第"+str(i+1)+"页===========")
            imgUrl = self.list_img()
            self.save_img(imgUrl)
            self.driver.find_element_by_link_text('下一页').click()


if __name__ == "__main__":
    img = getImg()
    img.run()