在网络爬取百度图片时遇到的问题

Question

问题遇到的现象和发生背景

问题相关代码，请勿粘贴截图

import os, re, requests
root = 'E:/PycharmProjects/pythonProhttps://img-mid.csdnimg.cn/release/static/image/mid/ask/862977902936192.png "#left")
ject/百度图片'
if not os.path.exists(root):
    os.makedirs(root)
pattern = r'"ObjURL":"(.*?)"'
pattern = re.compile(pattern)


def getTextFromHtml(url):
    cReturn = ""
    try:
        r = requests.get(url, timeout=30, headers={'Accept': 'application/json, text/javascript, */*; q=0.01','Accept-Encoding': 'gzip, deflate, br','Accept-Language': 'zh-CN,zh;q=0.9','Connection':'keep-alive','Sec-Fetch-Dest': 'empty','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.11261 SLBChan/103'})
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        cReturn = r.text
    except:
        cReturn = ''
    return cReturn


def download(List):
    for u in List:
        try:
            path=root+u.split('/')[-1]
            u = u.replace('\\', '')
            r = requests.get(u, timeout=30)
            r.raise_for_status()
            r.encoding = r.apparent_encoding
            if not os.path.exists(path):
                with open(path,'wb') as f:
                    f.write(r.content)
                    f.close()
                    print(path + ' 文件保存成功')
        except:
             print(u, "下载失败，可能链接不是指定格式图片")


def getOtherPage(nPage, nNum, word):
    urllist = []
    url = r'http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={word}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&word={word}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&pn={pn}&rn={rn}'

    for x in range(1, nPage + 1):
        u = url.format(word=word, pn=nNum * x, rn=nNum)
        urllist.append(u)
    return urllist

n = 30
page = int(input('输入想下载多少页图片（每页%d张图片）：' % (n)))
word = input('输入想下载的图片搜索关键字:')

url = 'http://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1499773676062_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word={word}'.format(word=word)
html = getTextFromHtml(url)
firstUrlList = re.findall(pattern, html)
download(firstUrlList)

otherUrlList = getOtherPage(page, n, word)
for i in range(page):
    html = getTextFromHtml(otherUrlList[i])
    url = re.findall(pattern, html)
    download(url)

运行结果及报错内容

我的解答思路和尝试过的方法

该代码能够运行，但无法进入try中

我想要达到的结果

Answer 1

download改下面这样就行了，保存的文件路径有问题，而且正则也搞错了，objURL，不是ObjURL，搞得没取出路径调试了下，发现大小写写错了，-_-||。。

def download(List):
    for u in List:
        try:
            #这里路径有问题，不是图片的问题，由于url中包含其他乱七八糟的路径中不能存在的内容，导致路径出错走了except。用当前时间来命名文件好些
            path=root+'/'+str(time.time())+".jpg"
            #u = u.replace('\\', '')
            r = requests.get(u, timeout=30)
            #r.raise_for_status()
            #r.encoding = r.apparent_encoding
            if not os.path.exists(path):
                with open(path,'wb') as f:
                    f.write(r.content)
                    f.close()
                    print(path + ' 文件保存成功')
        except:
             print(u, "下载失败，可能链接不是指定格式图片")

有帮助麻烦点下【采纳该答案】，谢谢~~