论坛的老哥要的东西！练手试了一下！
实现了图片一键（网址）下载，真正的懒人版工具，只要输入你想要获取的相册首页链接，图片基本到手！
又拍相册 https://x.yupoo.com
又拍图片管家-淘宝相册,图片空间,图片存储,专业的图片云计算服务
电商图片管家，还是有不少产品相册在里面！
尤其是我大莆田产品，谁卖谁知道，我买我知道！
PS：教你如何找产品相册！
http://rank.chinaz.com/?host=x.yupoo.com
点开有惊喜！！
注意鉴别骗子哈！
技术比较渣，见谅！
拿去玩！
适合想要获取 又拍云 相册图片的需求！
自己测试了一下，没有用多线程，可能速度还是比较low！
写了报错以及记录功能，如果没有下载到的图片，自己手动补上吧，失败的链接都写在spider.txt上！
运行测试：
网速比较慢，暂时只有这么多了，程序应该可以运行结束，有bug的话 可以留言回复私聊！
方便大哥们使用，弟弟已经给各位大佬，大哥们打包了一下exe程序，运行环境，win7 64位，其他系统环境不一定能运行哈！
exe百度云地址：
链接: https://pan.baidu.com/s/1BUo52myhLfRM22wQU2asxg 提取码: i7qd
又拍云相册图片采集助手使用说明：
1.打开yupoo.exe程序！
2.输入又拍云相册的首页地址，比如：https://chenxuezhen1989.x.yupoo.com！
3.回车运行即可！
4.采集失败链接记录在spider.txt，建议自行手动补图片!
需知：该程序运行环境为win7 64位
附上python源码：
#又拍图片管家
#https://735539381.x.yupoo.com爬取
# -*- coding: UTF-8 -*-
import requests,re,os,random,time
from lxml import etree
class Yupoo():
def __init__(self,url):
ua_list = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
]
self.ua=random.choice(ua_list)
self.url=url
#抓取首页相册全部分类链接
def get_categorylist(self):
headers={'user-agent': self.ua}
ceagortylists=[]
response=requests.get(self.url,headers=headers,timeout=5).text
time.sleep(1)
req=etree.HTML(response)
ceagortylist=req.xpath('//ul[@class="showheader__category"]/a/@href')
for list in ceagortylist:
list=f'{url}{list}'
ceagortylists.append(list)
print(ceagortylists)
print(f'相册分类数：{len(ceagortylists)}')
return ceagortylists
# 抓取相册链接
def get_urllists(self, ceagortylists):
headers = {'user-agent': self.ua}
for url in ceagortylists:
print(url)
try:
response = requests.get(url, headers=headers, timeout=5).text
time.sleep(1)
req = etree.HTML(response)
if "pagination__jumpwrap" in response:
print(f'{url}存在相册分页链接')
num=req.xpath('//form[@class="pagination__jumpwrap"]/span[1]/text()')[0]
num=num[1:-1]
print(num)
num=int(num)
print(f'共有{num}页分页！')
for i in range(1,num+1):
numurl=f'{url}?page={i}'
print(numurl)
try:
num_response = requests.get(numurl, headers=headers, timeout=5).text
time.sleep(1)
num_req = etree.HTML(num_response)
category_urllists = num_req.xpath('//div[@class="showindex__children"]/a[@class="album__main"]/@href')
for category_url in category_urllists:
category_url = f'{self.url}{category_url}'
try:
self.get_img(category_url)
except Exception as e:
print(f'采集产品相册页链接失败，错误代码：{e}')
with open(f'yupoo/spider.txt', 'a+', encoding='utf-8') as f:
f.write(f'{category_url}---产品相册页链接采集失败，错误代码：{e}')
except Exception as e:
print(f'采集相册分页链接失败，错误代码：{e}')
with open(f'yupoo/spider.txt', 'a+', encoding='utf-8') as f:
f.write(f'{numurl}---相册分页链接采集失败，错误代码：{e}')
else:
print(f'{url}没有相册分页链接')
category_urllists = req.xpath('//div[@class="showindex__children"]/a[@class="album__main"]/@href')
for category_url in category_urllists:
category_url = f'{self.url}{category_url}'
try:
self.get_img(category_url)
except Exception as e:
print(f'采集产品相册页链接失败，错误代码：{e}')
with open(f'yupoo/spider.txt', 'a+', encoding='utf-8') as f:
f.write(f'{category_url}---产品相册页链接采集失败，错误代码：{e}')
except Exception as e:
print(f'采集相册链接失败，错误代码：{e}')
with open(f'yupoo/spider.txt', 'a+', encoding='utf-8') as f:
f.write(f'{url}---相册链接采集失败，错误代码：{e}')
#采集相册详情内容
def get_img(self,url):
headers = {'user-agent': self.ua}
response = requests.get(url,headers=headers,timeout=5).text
time.sleep(1)
req = etree.HTML(response)
#采集标题
h2=req.xpath('//h2/span[@class="showalbumheader__gallerytitle"]/text()')[0]
h2= re.sub(r'[\|\/\<\>\:\*\?\\\"]', "_", h2) # 剔除不合法字符
print(h2)
#创建目录
os.makedirs(f'yupoo/{h2}/',exist_ok=True)
#采集文字详情
try:
text=req.xpath('//div[@class="showalbumheader__gallerysubtitle htmlwrap__main"]/text()')[0]
except Exception as e:
print(f'无详情文字内容！')
text=[]
print(text)
if text!=[]:
texts='%s%s%s'%(h2,'\n',text)
with open(f'yupoo/{h2}/{h2}.txt','w',encoding='utf-8') as f:
f.write(texts)
print(f'{h2}.txt 文档保存成功！')
#采集图片
imgurls=req.xpath('//div[@class="showalbum__children image__main"]/div[@class="image__imagewrap"]/img/@data-origin-src')
i=1
headers2 = {
'referer': url,
'user-agent': self.ua,
}
print(headers)
for imgurl in imgurls:
imgurl=f'https:{imgurl}'
print(imgurl)
if "jpeg" in imgurl:
imgname=f'{i}{imgurl[-5:]}'
elif "jgp" in imgurl or "png" in imgurl or "gif" in imgurl:
imgname = f'{i}{imgurl[-4:]}'
else:
imgname = f'{i}{imgurl[-4:]}'
print(imgname)
try:
r=requests.get(imgurl,headers=headers2,timeout=8)
with open(f'yupoo/{h2}/{imgname}','wb') as f:
f.write(r.content)
print(f'下载{imgname}图片成功！')
time.sleep(1)
except Exception as e:
print(f'下载{imgurl}图片失败，错误代码：{e}')
with open(f'yupoo/{h2}/spider.txt','a+',encoding='utf-8') as f:
f.write(f'访问相册{url}---{imgurl}---下载失败，错误代码：{e}')
i=i+1
print(f'采集 {h2} 图片成功！')
if __name__ == '__main__':
#url = "https://735539381.x.yupoo.com"
#url="https://chenxuezhen1989.x.yupoo.com"
url=input("请输入要爬取的又拍相册首页链接地址：")
print(f'爬虫启动中，请稍后......')
spider=Yupoo(url)
print(f'相册首页分类链接采集中，请稍后......')
ceagortylists=spider.get_categorylist()
print(f'相册首页分类链接采集完毕！')
time.sleep(2)
print(f'相册所有链接采集中，时间可能稍长，请稍后......')
spider.get_urllists(ceagortylists)
print(f'采集完毕，采集{url}图片成功！')
print(f'10后自动结束程序，退出！')
time.sleep(10)
