zbrj12345的博客

from selenium import webdriver import os,time from lxml import etree #豆瓣音乐 root_dir='douban' if not os.path.exists(root_dir): os.mkdir(root_dir) #访问 driver=webdriver.PhantomJS() base_url='https:...

#豆瓣登录 from selenium import webdriver from selenium.webdriver.common.action_chains import ActionChains import os,time driver=webdriver.PhantomJS() driver.get('https://www.douban.com/') #网络请求时间 time.sle...

from lxml import etree from urllib import request import ssl ssl._create_default_https_context=ssl._create_unverified_context html=''' <bookstore> <title>新华书店</title> <bo...

from urllib import request from lxml import etree import re import ssl import json ssl._create_default_https_context=ssl._create_unverified_context def spider(page): base_url='https://www.qiushi...

# -*- coding: utf-8 -*- import scrapy from urllib import request from Py06_2018_3_16.items import TencentItem class tencentNextPageSpider(scrapy.Spider): name = 'tencent_next_page' allowed_do...

# -*- coding: utf-8 -*- import scrapy,re,os from PY_2018_03_17.items import TuKuItem from urllib import request class TukuSpider(scrapy.Spider): name = 'tuku' allowed_domains = ['lanrentuku.c...