卓越飞翔博客卓越飞翔博客

卓越飞翔 - 您值得收藏的技术分享站
技术文章11201本站已运行3223

【python】写真网站小姐姐图片集合打包下载

缺点:
1、下载的图片都在一个文件夹内,虽然已经排序了,但是没做到一个图集新建一个文件夹保存
2、想要加入多线程,技术有限,一直不成功,爬取的速度并不快
3、在爬取了300-400张图片左右,会报错停止程序,显示连接不上主机,试过2次都是这样

写的比较简单,问题很多,烦请论坛大佬们赐教//////
 

#秀人网图片爬虫
import urllib
import urllib.request
from lxml import etree
import requests
import random
import threading
import time
 
USER_AGENTS = [
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
    "UCWEB7.0.2.37/28/999",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
]
 
headers={'User-Agent': random.choice(USER_AGENTS)}
 
 
class Spider(object):
    def __init__(self):
        self.mtName="熊小诺"  #易阳薇薇鱼子酱熊小诺
        self.title="title"
        self.beginPage=1
        self.endPage=7
        self.url="https://www.xrmnw.cc/plus/search/index.asp?"
        self.ua_header=headers            #{"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1 Trident/5.0;"}
        self.fileName=1
 
# [url=https://www.xrmnw.cc/plus/search/index.asp?keyword=%E7%86%8A%E5%B0%8F%E8%AF%BA&searchtype=title&p=1]https://www.xrmnw.cc/plus/search/index.asp?keyword=%E7%86%8A%E5%B0%8F%E8%AF%BA&searchtype=title&p=1[/url]
# [url=https://www.xrmnw.cc/plus/search/index.asp?keyword=%E7%86%8A%E5%B0%8F%E8%AF%BA&searchtype=title&p=2]https://www.xrmnw.cc/plus/search/index.asp?keyword=%E7%86%8A%E5%B0%8F%E8%AF%BA&searchtype=title&p=2[/url]
 
    #url
    def tiebaSpider(self):
        for page in range(self.beginPage,self.endPage+1):
            try:
                sea=page
                #get
                wo={'keyword':self.mtName,'searchtype':self.title,'p':sea}
                word=urllib.parse.urlencode(wo)
                myurl=self.url+word
            except Exception as e:
                pass
            self.loadPage(myurl)
 
    #爬取页面
    def loadPage(self,myurl):
        req=urllib.request.Request(myurl,headers=self.ua_header)
        data=urllib.request.urlopen(req).read()
        html=etree.HTML(data)
        links=html.xpath('//div[@class="title"]/h2/a/@href')
 
 
        for link in links:
            try:
                link="https://www.xrmnw.cc"+link
            except Exception as e:
                pass
            self.loadImages(link)
 
    #爬取帖子
    def loadImages(self,link):
        req=urllib.request.Request(link,headers=self.ua_header)
        data=urllib.request.urlopen(req).read()
         
        #爬取详情页
        html=etree.HTML(data)
        links=html.xpath('//div[@class="content"]/div/div/a/@href')
        #爬取标题
        cun_name=html.xpath('//h1')
        #print(cun_name[0].text)
 
        for imageslink in links:
            try:
                linkss="https://www.xrmnw.cc"+imageslink
                print(linkss)
            except Exception as e:
                pass
            self.idImages(linkss)
 
    #获得图片
    def idImages(self,linkss):
        req=urllib.request.Request(linkss,headers=self.ua_header)
        data=urllib.request.urlopen(req).read()
 
        html=etree.HTML(data)
        links=html.xpath('//div[@class="content_left"]/p/img/@src')
        for imagesID in links:
            linkID="https://www.xrmnw.cc"+imagesID
            self.writeImages(linkID)
 
    #保存
    def writeImages(self,linkID):
        print("正在存储图片:",self.fileName,"....")
 
        image=urllib.request.urlopen(linkID).read()
 
        file=open(r"E:\360驱动大师目录\测试下载文件\\"+str(self.fileName)+".jpg","wb")
        file.write(image)
 
        file.close()
 
        self.fileName+=1
 
if __name__ == '__main__':
 
    mySpider=Spider() 
 
    mySpider.tiebaSpider() 
卓越飞翔博客
上一篇: [Python 原创] 抖音爬虫(主页、喜欢列表全部下载)
下一篇: C# 最新快手无水印解析 支持背景音乐 (可搭建网站)
留言与评论(共有 0 条评论)
   
验证码:
隐藏边栏