import os, re, requests

root = 'D:/Python/download/'		# 图片文件夹
if not os.path.exists(root):
    os.makedirs(root)

pattern = r'"ObjURL":"(.*?)"'	# 匹配图片链接的正则表达式
pattern = re.compile(pattern)


# 获取url对应的源码页面内容
def getTextFromHtml(url):
    cReturn = ""
    try:
        r = requests.get(url, timeout=30, headers={'user-agent': 'mozilla/5.0'})
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        cReturn = r.text
    except:
        cReturn = ''
    return cReturn


# 下载图片（url列表）
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 = []
#链接接口
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 = int(input('输入每页显示多少张图片：'))
n = 30	# 手工设置每页30张图片
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:')
#链接接口
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)