Download subtitles from shooter

shooter.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import hashlib
import sys
import math
import json
import urllib2
import urllib

try:
    import chardet
except ImportError:
    print 'Install chardet via `pip install chardet`'
    sys.exit(1)


def download(url, headers):
    req = urllib2.Request(url, '', headers)
    return urllib2.urlopen(req).read()

def get_hash(name):
    L = list()
    with open(name, 'rb') as f:
        e = 4096
        f.seek(0, os.SEEK_END)
        size = f.tell()

        # first 4k
        start = min(size, 4096)
        end = min(start + e, size)
        f.seek(int(start))
        data = f.read(int(end - start))
        digest = hashlib.md5(data).hexdigest()
        L.append(digest)

        # second 4k
        start = math.floor(size / 3 * 2)
        end = min(start + e, size)
        f.seek(int(start))
        data = f.read(int(end - start))
        digest = hashlib.md5(data).hexdigest()
        L.append(digest)

        # third 4k
        start = math.floor(size / 3)
        end = min(start + e, size)
        f.seek(int(start))
        data = f.read(int(end - start))
        digest = hashlib.md5(data).hexdigest()
        L.append(digest)

        # fourth 4k
        start = max(0, size - 8192)
        end = min(start + e, size)
        f.seek(int(start))
        data = f.read(int(end - start))
        digest = hashlib.md5(data).hexdigest()
        L.append(digest)

    return L


def sub_downloader(path, lang):
    dirname = os.path.dirname(path)
    filename = os.path.basename(path)

    name, ext = os.path.splitext(filename)
    if ext not in [".mkv", ".avi", ".mp4"]:
        return

    hash = get_hash(path)
    headers = {'User-Agent': 'wyyqyl'}

    filehash = hash[0] + '%3B' + hash[1] + '%3B' + hash[2] + '%3B' + hash[3]
    url = 'http://www.shooter.cn/api/subapi.php?filehash=' + filehash + '&format=json&pathinfo=' + urllib.pathname2url(filename) + '&lang=' + lang
    print url
    response = download(url, headers)
    if ord(response[0]) == 0xff:
        print '❌ [{}] It doesn\'t exist'.format(lang)
        return
    print '📢 [{}] It exists, downloading'.format(lang)

    sub_infos = json.loads(response)
    idx = 0
    for sub_info in sub_infos:
        if 'Files' in sub_info:
            success = False
            for file_info in sub_info['Files']:
                try:
                    url = file_info['Link'].replace('\u0026', '&')
                    content = download(url, headers)
                    encoding = chardet.detect(content).get('encoding')
                    if encoding == None:
                        # Is it UTF-16LE without BOM?
                        encoding = chardet.detect('\xFF\xFE' + content).get('encoding')
                    if encoding == None:
                        # Is it UTF-16BE without BOM?
                        encoding = chardet.detect('\xFE\xFF' + content).get('encoding')
                    if encoding == None:
                        # I got no idea, skip downloading subtitle
                        continue
                    content = content.decode(encoding, 'ignore').encode('utf-8')
                    subtitle_name = name + '.' + lang + "." + str(idx) + "." + file_info['Ext']
                    with open(os.path.join(dirname, subtitle_name), 'wb') as subtitle:
                        subtitle.write(content)
                        success = True
                except Exception as e:
                    print e
                    print '❌ [{}] Error occured'.format(lang)
            if success:
                idx += 1
    print '✅ [{}] {} subtitles downloaded'.format(lang, idx)


def main():
    for root, _, files in os.walk(sys.argv[1]):
        for file in files:
            path = os.path.join(root, file)
            print '💪 Processing {}'.format(path)
            for lang in ['chn', 'eng']:
                sub_downloader(path, lang)
            print '\n'


if __name__ == "__main__":
    main()