'''
图片混淆,对图片解析
如果图片识别不准确，需要升级OCR库
6.1
'''
from common.tools import Tool
import requests
from scrapy.selector import Selector
from urllib import parse
class ImgSpider:
    def __init__(self):
        self.tool = Tool.get_tool()

    def run(self):
        url = 'http://www.porters.vip/confusion/recruit.html#'
        headers = {}
        headers = self.tool.get_user_agent(headers)
        r = requests.get(url=url,headers=headers)
        if r.status_code == 200:
            img = Selector(r).xpath('//img[@class="pn"]/@src').extract_first()
            img = parse.urljoin(r.url,img)
            # img = 'https://vip.gxrc.com/Public/Phone/3678B85A-6C0B-42D6-B5C7-3D6D89450001'
            test = self.tool.tessseract_img(img)
            print('图片字体为：{}'.format(test))

if __name__ == '__main__':
    ImgSpider().run()

----参考python3反爬虫原理与绕过实战