selenium&phantomjs实战--漫话爬取

为什么直接保存当前网页，而不是找到所有漫话链接，再有针对性的保存图片？

因为防盗链的原因，当直接保存漫话链接图片时，只能保存到防盗链的图片。

#!/usr/bin/env python

# _*_ coding: utf-8 _*_

# __author__ ='kong'

from selenium import webdriver

import os

import time

class GetCartoon(object):

    def __init__(self):

        self.startUrl = "http://www.1kkk.com/ch1-406302/"

        self.browser = self.getBrowser()

        self.saveCartoon()

    def getBrowser(self):

        browser = webdriver.PhantomJS()

        try:

            browser.get(self.startUrl)

            browser.implicitly_wait(5)

            print "url get ok"

        except:

            print "url get failed"

        return browser

    def createDir(self,fileName):

        if os.path.exists(fileName):

            print "dir is exists"

        else:

            os.makedirs(fileName)

            print "dir create ok"

    def saveCartoon(self):

        fileName = self.browser.title.split("_")[0]

        self.createDir(fileName)

        os.chdir(fileName)

        # 总共26页

        sumPage = int(self.browser.find_element_by_xpath("//font[@class='zf40']/span[2]").text)

        i = 1

        while i <= sumPage:

            imgName = str(i)+'.png'

            # html页面保存成图片

            self.bowser.get_screenshot_as_file(imgName)

            i += 1

            # 点击下一页按扭

            NextTag = self.browser.find_element_by_id("next")

            NextTag.click()

            # 3秒后执行保存图片操作

            time.sleep(3)

        self.browser.close()

if __name__ == '__main__':

    GC = GetCartoon()