[Python] 纯文本查看 复制代码
# -*- 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('//div[@class="show-layout-category__catewrap"]/a/@href')
for list in ceagortylist:
list=f'{url}{list}'
ceagortylists.append(list)
print(ceagortylists)
return ceagortylists
#抓取相册所有链接
def get_urllist(self,ceagortylists):
headers = {'user-agent': self.ua}
category_lists=[]
for url in ceagortylists:
response = requests.get(url,headers=headers,timeout=5).text
time.sleep(1)
req = etree.HTML(response)
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}'
category_lists.append(category_url)
print(category_lists)
return category_lists
#采集图片
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)
h2=req.xpath('//h2/span[@class="showalbumheader__gallerytitle"]/text()')[0]
h2= re.sub(r'[\|\/\<\>\:\*\?\\\"]', "_", h2) # 剔除不合法字符
print(h2)
os.makedirs(f'yupoo/{h2}/',exist_ok=True)
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
if __name__ == '__main__':
#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......')
category_lists=spider.get_urllist(ceagortylists)
print(f'相册所有链接采集完毕！')
print(f'正在采集相册图片......')
for url in category_lists:
try:
spider.get_img(url)
print(f'恭喜！采集{url}网页图片成功！')
except Exception as e:
print(f'采集网页图片失败，错误代码：{e}')
with open(f'yupoo/spider.txt', 'a+', encoding='utf-8') as f:
f.write(f'{url}---采集失败，错误代码：{e}')
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)
[复制链接]
发表于 2019-11-6 17:55
|
发表于 2019-11-16 17:30
exe 可以运行~
额 没有考虑到这样的情况 首页还有分页 那就一页页贴进去吧！ 
