api-loadercdn/tiny.py at master · fredhdx/api-loadercdn · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
import os
from bs4 import BeautifulSoup
from urllib.parse import urlparse
import re
import requests
import time
import sys

"""
给所有下载的文件夹添加tag文件, 记录更多信息便于辨认
为ｂ站下载重新命名

"""

# 得到bilibili视频名称和分ｐ名称
def bilibili_namer(bili_url):
    """
    Find out the real video name
    """
    request_timeout = 60
    title = ""
    subtitle=""

    if "www.bilibili.com/video/av" in bili_url:
        start_time = time.time()
        while True:
            try:
                r = requests.get(bili_url)
                break
            except requests.exceptions.ConnectionError:
                if time.time() - start_time > request_timeout:
                    print("bilibili_namer timeout: unable to connect after %s s" % request_timeout)
                    return [title,subtitle]
                else:
                    time.sleep(1)

        soup = BeautifulSoup(r.text,"lxml")
        title = soup.findAll('div',{'class':'v-title'})[0].text

        if soup.findAll('option'):
            if re.search(r'.*/video/av(\d+)(/)?$', bili_url):
                bili_url = (bili_url + '/index_1.html' if re.search(r'av(\d+)$', bili_url)
                            else bili_url + 'index_1.html')

            p_str = urlparse(bili_url).path # get /video/av/index.html
            search = soup.findAll('option',{"value":p_str})
            if search:
                subtitle = soup.findAll('option',{"value":p_str})[0].text[2:]
            else:
                print("%s out of range. 无效链接" % p_str)
                return [title,subtitle]

        return [title,subtitle]
    else:
        print("Not valid bilibili video link")
        return [title,subtitle]

# 给所有已下载的ｂ站视频添加info log,记录名称、分ｐ名称、网址
def log_all(inputfile):
    input_file = open(inputfile,'r')
    URLs = []
    URLs.extend([x for x in input_file.read().splitlines() if x])

    for uri in URLs:
        print(uri)
        rtitle,rsub_title = bilibili_namer(uri)
        newtitle = rtitle + ' ' + rsub_title if rsub_title else rtitle

        old_dir = os.getcwd() + os.path.sep + "downloaded" + os.path.sep + rtitle

        if os.path.isdir(old_dir):
            log_path = old_dir + os.path.sep + "info.log"
            if not os.path.isfile(log_path):
                _log = open(log_path, 'w')
                _log.write(rtitle + '\n')
                _log.write(rsub_title + '\n')
                _log.write(uri)
                _log.close()


# 给已下载b站视频重新命名: "视频名称" <---> "视频名称 分P名称"
def rename_all(inputfile):
    input_file = open(inputfile,'r')
    URLs = []
    URLs.extend([x for x in input_file.read().splitlines() if x])

    for uri in URLs:
        print(uri)
        rtitle,rsub_title = bilibili_namer(uri)
        newtitle = rtitle + ' ' + rsub_title if rsub_title else rtitle

        old_dir = os.getcwd() + os.path.sep + "downloaded" + os.path.sep + rtitle
        new_dir = os.getcwd() + os.path.sep + "downloaded" + os.path.sep + newtitle

        if os.path.isdir(old_dir):
            old_file = old_dir + os.path.sep + rtitle + '.ogg'
            new_file = old_dir + os.path.sep + newtitle + '.ogg'
            if os.path.isfile(new_file):
                print("renaming %s > %s" % (old_file.split('/')[-1],new_file.split('/')[-1]))
                #input()
                os.rename(old_file,new_file)

            print("renaming folder %s > %s" % (old_dir.split('/')[-1], new_dir.split('/')[-1]))
            #input()
            os.rename(old_dir, new_dir)

if __name__ == "__main__":
    list_file = "listaa"
    # rename_all(list_file)
    log_all(list_file)