python中如何实现一键爬取淘宝天猫宝贝页面主图颜色图和详情图-创新互联
这篇文章将为大家详细讲解有关python中如何实现一键爬取淘宝天猫宝贝页面主图颜色图和详情图,小编觉得挺实用的,因此分享给大家做个参考,希望大家阅读完这篇文章后可以有所收获。
创新互联公司致力于互联网品牌建设与网络营销,包括网站建设、网站设计、SEO优化、网络推广、整站优化营销策划推广、电子商务、移动互联网营销等。创新互联公司为不同类型的客户提供良好的互联网应用定制及解决方案,创新互联公司核心团队十年专注互联网开发,积累了丰富的网站经验,为广大企业客户提供一站式企业网站建设服务,在网站建设行业内树立了良好口碑。实例如下所示:
import requests import re,sys,os import json import threading import pprint class spider: def __init__(self,sid,name): self.id = sid self.headers = { "Accept":"text/html,application/xhtml+xml,application/xml;", "Accept-Encoding":"gzip", "Accept-Language":"zh-CN,zh;q=0.8", "Referer":"http://www.example.com/", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36" } self.name=name def openurl(self,url): self.request = requests.get(url,headers = self.headers) if self.request.ok: return self.request.text def matchs(self): tmall_exp = r"Setup\(([\s\S]+?)\);"### 匹配商品数据的正则 detail= r"src=\"(https://img\S+?[jpgifn]+?)\"" ###匹配 商品详情图的正则 html = self.openurl("https://detail.tmall.com/item.htm?id=%s"%self.id) data = re.findall(tmall_exp,html) data = json.loads(data[0]) main_img = data['propertyPics'] ## 这里包括了主图和颜色图的地址 color_data =data['valItemInfo'] ['skuList'] ### 这里获得商品的颜色信息列表 包括颜色编码 颜色名称,商品skuID detail_html = self.openurl("http:"+data['api']["httpsDescUrl"]) detail_image = re.findall(detail,detail_html) self.newdata={"MAIN":main_img['default'],"DETAIL":detail_image,"id":self.id,} psvs = [] self.newdata['COLOR']=[] for v in range(len(color_data)): if ";"in color_data[v]["pvs"]: psv = color_data[v]['pvs'][color_data[v]['pvs'].find(";")+1:] else: psv = color_data[v]['pvs'] if psv in psvs: continue psvs.append(psv) self.newdata['COLOR'].append({color_data[v]["names"]:main_img[";"+psv+";"]}) pprint.pprint(self.newdata) return self.newdata def download(self): if len(self.newdata)>0: for x in range(len(self.newdata['MAIN'])): threading.Thread(target=self.download_main,args=(self.newdata['MAIN'][x],x)).start() for x in self.newdata['COLOR']: threading.Thread(target=self.download_color,args=(x,)).start() for x in range(len(self.newdata['DETAIL'])): threading.Thread(target=self.download_detail,args=(self.newdata['DETAIL'][x],x)).start() return def download_main(self,url,index): try: img = requests.get("http:"+url,stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/main"): try: os.makedirs(self.name+"/main") except: pass imgs = open(self.name+"/main/%s.jpg"%index,"wb") imgs.write(img.content) imgs.close() def download_color(self,url): try: img = requests.get("http:"+url[list(url.keys())[0]][0],stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/color"): try: os.makedirs(self.name+"/color") except: pass if "/"in list(url.keys())[0]: color = list(url.keys())[0].replace("/","_") elif "\\" in list(url.keys())[0]: color = list(url.keys())[0].replace("\\","_") else: color = list(url.keys())[0] imgs = open(self.name+"/color/%s.jpg"%color,"wb") imgs.write(img.content) imgs.close() def download_detail(self,url,index): try: img = requests.get(url,stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/detail"): try: os.makedirs(self.name+"/detail") except: pass imgs = open(self.name+"/detail/%s.jpg"%index,"wb") imgs.write(img.content) imgs.close() if __name__ =="__main__": sid = 528766269341 ## 这里输入天猫宝贝ID taobao = spider(sid,"下载图片/T") taobao.matchs() taobao.download()
关于“python中如何实现一键爬取淘宝天猫宝贝页面主图颜色图和详情图”这篇文章就分享到这里了,希望以上内容可以对大家有一定的帮助,使各位可以学到更多知识,如果觉得文章不错,请把它分享出去让更多的人看到。
当前文章:python中如何实现一键爬取淘宝天猫宝贝页面主图颜色图和详情图-创新互联
文章网址:http://cdiso.cn/article/djesdh.html