import os
import chardet
import codecs
import re


def WriteFile(filePath, u, encoding="utf-8"):
    with codecs.open(filePath, "w", encoding) as f:
        print(filePath)
        f.write(u)


def convert(src, dst):
    #     检测编码，coding可能检测不到编码，有异常
    f = open(src, "rb")
    coding = chardet.detect(f.read())["encoding"]
    f.close()
    with codecs.open(src, "r", coding) as f:
        try:
            pattern = 'href="javascript:if\(confirm\([^"]*"'
            pattern_url='(https?|ftp|file)://[-A-Za-z0-9+&@#/%?=~_|!:,.;]+[-A-Za-z0-9+&@#/%=~_|]'
            data = f.read()
            # 获取所有正则匹配
            out = re.findall(pattern, data, flags=0)
            if out:
                for eachOut in out :
                    # 取出每个链接
                    url='href="'+re.search(pattern_url,eachOut,flags=0).group()+'"'
                    data=data.replace(eachOut, url)
            WriteFile(dst, data, encoding="utf-8")
        except Exception:
            print(src + "  " + coding + "  read error")

# 把目录中的*.java编码由gbk转换为utf-8


def fix(rootdir):
    for parent, dirnames, filenames in os.walk(rootdir):
        for dirname in dirnames:
                # 递归函数，遍历所有子文件夹
            fix(dirname)
        for filename in filenames:
            if filename.endswith(".html"):
                convert(os.path.join(parent, filename),
                        os.path.join(parent, filename))


if __name__ == "__main__":
    src_path = "E:/share/linux/100/www.100.me"
    fix(src_path)