ygdwb的博客

from selenium import webdriver from lxml import etree import tesserocr import numpy as np import time from PIL import Image import matplotlib.pylab as plt import matplotlib.image as mpimg #加载谷歌驱动程序 bro=webdriver.Chrome(executable_path='D:\python\Reptiliane

import scrapy from selenium import webdriver from sohuPro.items import SohuproItem class SohuSpider(scrapy.Spider): name = 'sohu' # allowed_domains = ['www.xxx.com'] start_urls = ['http://sports.sina.com.cn/'] #需求：爬取新浪体育欧冠,西甲，意甲，德甲等5大板块中的新闻