【Pyhton】------ 爬取图片示例代码

﹏ヽ暗。殇╰゛Y 2023-01-19 12:58 129阅读 0赞

>     import os
>     import re
>     
>     import requests
>     import json
>     from lxml import etree
>     import urllib
>     from bs4 import BeautifulSoup
>     
>     #下载图片
>     def getSogouImagDowld(htmlsrc,filename,path):
>         imgHtml = requests.get(htmlsrc)
>         soup = BeautifulSoup(imgHtml.text, 'html.parser')
>         imgSrcHtml = soup.select('.photo-information-content img')
>         m=0
>         for i in imgSrcHtml:
>            selector = etree.HTML(str(i))
>            imgsrc = selector.xpath('//img/@src')[0]
>            print('***** '+imgsrc+' *****'+'   Downloading...')
>            try:
>                urllib.request.urlretrieve(imgsrc, path + filename + '/' + str(m) + '.jpg')
>                m = m + 1
>                print('Download complete!')
>            except IOError:
>                print ("没有找到文件")
>     
>     
>     #获取图片
>     
>     def getSogouImag(page,limit,path):
>     
>         vpage = page
>         vlimit= limit
>         # imgs = requests.get('https://www.zcool.com.cn/discover.json?cate=1&subCate=7&hasVideo=0&city=0&college=0&recommendLevel=2&sort=9&limit=200&page=1')
>         imgs = requests.get('https://www.zcool.com.cn/search/content.json?word=nutdream&cate=0&type=0&recommendLevel=0&time=0&hasVideo=0&city=0&college=0&sort=5&limit=25&column=5&page=1')
>         jd = json.loads(imgs.text)
>         jdData = jd['data']["data"]
>         # jdData = jd['data']
>         html_url = []
>         file_name = []
>     
>         #保留网址
>         for jd_json in jdData:
>             if 'pageUrl' in jd_json['object']:
>               pageUrlstr=jd_json['object']['pageUrl']
>               fileName=jd_json['object']['title'].strip()
>               fileName=re.sub('[a-zA-Z0-9"#$%&\'()*+,-./:;<=>?@，。?★、…【】《》？“”‘[\\]^_`{|}~\s]+','', fileName)
>               html_url.append(pageUrlstr)
>               file_name.append(fileName)
>     
>         #创建文件夹
>         for fileValue in file_name:
>             print('***** ' + str(fileValue) + ' 创建文件夹 *****' + '   Createloading...')
>             fileDY=path+fileValue
>             isExists = os.path.exists(fileDY)
>             # 判断结果 不存在就创建
>             if not isExists:
>                 os.makedirs(fileDY)
>     
>         #下载图片
>         fileNum=0
>         for url in html_url:
>             print('***** ' + str(url) + ' 下载图片中 *****' + '   downloadloading...')
>             filename=file_name[fileNum]
>             getSogouImagDowld(url,filename,path)
>             fileNum=fileNum+1
>     
>     
>     getSogouImag(200,1,'D:/nutdream/')
> 
> 效果图：
> 
> ![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM4MzY2NjU3_size_16_color_FFFFFF_t_70][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM4MzY2NjU3_size_16_color_FFFFFF_t_70]: /images/20221021/d87f5cab8fbf49b4a1df978e75f48e1e.png