重庆分公司,新征程启航
为企业提供网站建设、域名注册、服务器等服务
以下是爬取京东商品详情的Python3代码,以excel存放链接的方式批量爬取。excel如下
10多年的神池网站建设经验,针对设计、前端、开发、售后、文案、推广等六对一服务,响应快,48小时及时工作处理。全网营销推广的优势是能够根据用户设备显示端的尺寸不同,自动调整神池建站的显示方式,使网站能够适用不同显示终端,在浏览器中调整网站的宽度,无论在任何一种浏览器上浏览网站,都能展现优雅布局与设计,从而大程度地提升浏览体验。创新互联从事“神池网站设计”,“神池网站推广”以来,每个客户项目都认真落实执行。
代码如下
from selenium import webdriver from lxml import etree from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys import datetime import calendar import logging from logging import handlers import requests import os import time import pymssql import openpyxl import xlrd import codecs class EgongYePing: options= webdriver.FirefoxOptions() fp= webdriver.FirefoxProfile() fp.set_preference("browser.download.folderList",2) fp.set_preference("browser.download.manager.showWhenStarting",False) fp.set_preference("browser.helperApps.neverAsk.saveToDisk","application/zip,application/octet-stream") global driver driver= webdriver.Firefox(firefox_profile=fp,options=options) def Init(self,url,code): print(url.strip()) driver.get(url.strip()) #driver.refresh() # 操作浏览器属于异步,在网络出现问题的时候。可能代码先执行。但是请求页面没有应答。所以硬等 time.sleep(int(3)) html= etree.HTML(driver.page_source) if driver.title!=None: listImg=html.xpath('//*[contains(@class,"spec-list")]//ul//li//img') if len(listImg)==0: pass if len(listImg)>0: imgSrc='' for item in range(len(listImg)): imgSrc='https://img14.360buyimg.com/n0/'+listImg[item].attrib["data-url"] print('头图下载:'+imgSrc) try: Headers= {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/ Firefox/50.0'} r= requests.get(imgSrc, headers=Headers, stream=True) if r.status_code == 200: imgUrl='' if item==0: imgUrl+=code + "_主图_" + str(item) + '.' + imgSrc.split('//')[1].split('/')[len(imgSrc.split('//')[1].split('/'))-1].split('.')[1] else: imgUrl+=code + "_附图_" + str(item) + '.' + imgSrc.split('//')[1].split('/')[len(imgSrc.split('//')[1].split('/'))-1].split('.')[1] open(os.getcwd()+'/img/'+ imgUrl , 'wb').write(r.content) # 将内容写入图片 del r except Exceptionas e: print("图片禁止访问:"+imgSrc) listImg=html.xpath('//*[contains(@class,"ssd-module")]') if len(listImg)==0: listImg=html.xpath('//*[contains(@id,"J-detail-content")]//div//div//p//img') if len(listImg)==0: listImg=html.xpath('//*[contains(@id,"J-detail-content")]//img') if len(listImg)>0: for index in range(len(listImg)): detailsHTML=listImg[index].attrib if 'data-id' in detailsHTML: try: details= driver.find_element_by_class_name("animate-"+listImg[index].attrib['data-id']).value_of_css_property('background-image') details=details.replace('url(' , ' ') details=details.replace(')' , ' ') newDetails=details.replace('"', ' ') details=newDetails.strip() print("详情图下载:"+details) try: Headers= {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/ Firefox/50.0'} r= requests.get(details, headers=Headers, stream=True) if r.status_code == 200: imgUrl='' imgUrl+=code + "_详情图_" + str(index) + '.' + details.split('//')[1].split('/')[len(details.split('//')[1].split('/'))-1].split('.')[1] open(os.getcwd()+'/img/'+ imgUrl, 'wb').write(r.content) # 将内容写入图片 del r except Exceptionas e: print("图片禁止访问:"+details) except Exceptionas e: print('其他格式的图片不收录'); if 'src' in detailsHTML: try: details= listImg[index].attrib['src'] if 'http' in details: pass else: details='https:'+details print("详情图下载:"+details) try: Headers= {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/ Firefox/50.0'} r= requests.get(details, headers=Headers, stream=True) if r.status_code == 200: imgUrl='' imgUrl+=code + "_详情图_" + str(index) + '.' + details.split('//')[1].split('/')[len(details.split('//')[1].split('/'))-1].split('.')[1] open(os.getcwd()+'/img/'+ imgUrl, 'wb').write(r.content) # 将内容写入图片 del r except Exceptionas e: print("图片禁止访问:"+details) except Exceptionas e: print('其他格式的图片不收录'); print('结束执行') @staticmethod def readxlsx(inputText): filename=inputText inwb= openpyxl.load_workbook(filename) # 读文件 sheetnames= inwb.get_sheet_names() # 获取读文件中所有的sheet,通过名字的方式 ws= inwb.get_sheet_by_name(sheetnames[0]) # 获取第一个sheet内容 # 获取sheet的最大行数和列数 rows= ws.max_row cols= ws.max_column for r in range(1,rows+1): for c in range(1,cols): if ws.cell(r,c).value!=None and r!=1 : if 'item.jd.com' in str(ws.cell(r,c+1).value) and str(ws.cell(r,c+1).value).find('i-item.jd.com')==-1: print('支持:'+str(ws.cell(r,c).value)+'|'+str(ws.cell(r,c+1).value)) EgongYePing().Init(str(ws.cell(r,c+1).value),str(ws.cell(r,c).value)) else: print('当前格式不支持:'+(str(ws.cell(r,c).value)+'|'+str(ws.cell(r,c+1).value))) pass pass if __name__ == "__main__": start= EgongYePing() start.readxlsx(r'C:\Users\newYear\Desktop\爬图.xlsx')