前言

使用Python爬取任意网页的资源文件，比如图片、音频、视频；一般常用的做法就是把网页的HTML请求下来通过XPath或者正则来获取自己想要的资源，这里我做了一个爬虫工具软件，可以一键爬取资源媒体文件；但是需要说明的是，这里爬取资源文件只针对HTML已有的文件，如果需要二次请求的是爬取不到的，比如酷狗音乐播放界面，因为要做通用工具，匹配不同的网站！！！😀😀😀

这里主推图片爬取，一些需要图片素材的可以输入网址一键爬取！

还有就是爬取视频的时候会把磁力链接爬取下来！可以使用第三方下载工具下载！🤗

代码

爬取资源文件

这里需要说明的就只，有的图片资源并不是url链接，是data:image格式，这里需要转换一下存储！

def getResourceUrlList(url ,isImage, isAudio, isVideo):
    global imgType_list, audioType_list, videoType_list
    imageUrlList = []
    audioUrlList = []
    videoUrlList = []
 
    url = url.rstrip().rstrip('/')
    htmlStr = str(requestsDataBase(url))
    # print(htmlStr)
    
    Wopen = open('reptileHtml.txt','w')
    Wopen.write(htmlStr)
    Wopen.close()
 
    Ropen = open('reptileHtml.txt','r')
    imageUrlList = []
 
    for line in Ropen:
        line = line.replace("'", '"')
        segmenterStr = '"'
        if "'" in line:
            segmenterStr = "'"
 
        lineList = line.split(segmenterStr)
        for partLine in lineList:
            if isImage == True:
                # 查找图片
                if 'data:image' in partLine:
                    base64List = partLine.split('base64,')
                    imgData = base64.urlsafe_b64decode(base64List[-1] + '=' * (4 - len(base64List[-1]) % 4))
                    base64ImgType = base64List[0].split('/')[-1].rstrip(';')
                    imageName = zfjTools.getTimestamp() + '.' + base64ImgType
                    imageUrlList.append(imageName + '$==$' + base64ImgType)
 
                # 查找图片
                for imageType in imgType_list:
                    if imageType in partLine:
                        imgUrl = partLine[:partLine.find(imageType) + len(imageType)].split(segmenterStr)[-1]
 
                        # 修复URL
                        imgUrl = repairUrl(imgUrl, url)
 
                        sizeType = '_{' + 'size' + '}'
                        if sizeType in imgUrl:
                            imgUrl = imgUrl.replace(sizeType, '')
 
                        imgUrl = imgUrl.strip()
 
                        if imgUrl.startswith('http://') or imgUrl.startswith('https://') and imgUrl not in imageUrlList:
                            imageUrlList.append(imgUrl)
                        else:
                            imgUrl = ''
 
            if isAudio == True:
                # 查找音频
                for audioType in audioType_list:
                    if audioType in partLine or audioType.lower() in partLine:
                        audioType = audioType.lower() if audioType.lower() in partLine else audioType
                        audioUrl = partLine[:partLine.find(audioType) + len(audioType)].split(segmenterStr)[-1]
 
                        # 修复URL
                        audioUrl = repairUrl(audioUrl, url)
 
                        if audioUrl.startswith('http://') or audioUrl.startswith('https://') and audioUrl not in audioUrlList:
                            audioUrlList.append(audioUrl)
                        else:
                            audioUrl = ''
 
            if isVideo == True:
                # 查找视频
                for videoType in videoType_list:
                    if videoType in partLine or videoType.lower() in partLine:
                        videoType = videoType.lower() if videoType.lower() in partLine else videoType
                        videoUrl = partLine[:partLine.find(videoType) + len(videoType)].split(segmenterStr)[-1]
 
                        # 修复URL
                        videoUrl = repairUrl(videoUrl, url)
 
                        if videoUrl.startswith('http://') or videoUrl.startswith('https://') or videoUrl.startswith('ed2k://') or videoUrl.startswith('magnet:?') or videoUrl.startswith('ftp://') and videoUrl not in videoUrlList:
                            videoUrlList.append(videoUrl)
                        else:
                            videoUrl = ''
 
    return (imageUrlList, audioUrlList, videoUrlList)

爬取自定义节点

# 统配节点爬取
def getNoteInfors(url, fatherNode, childNode):
    url = url.rstrip().rstrip('/')
    htmlStr = requestsDataBase(url)
    
    Wopen = open('reptileHtml.txt','w')
    Wopen.write(htmlStr)
    Wopen.close()

    html_etree = etree.HTML(htmlStr)

    dataArray = []

    if html_etree != None:
        nodes_list = html_etree.xpath(fatherNode)
        for k_value in nodes_list:
            partValue = k_value.xpath(childNode)
            if len(partValue) > 0:
                dataArray.append(partValue[0])

    return dataArray