1
|
1 |
|
import logging |
2
|
1 |
|
import re |
3
|
1 |
|
import subprocess |
4
|
1 |
|
import sys |
5
|
|
|
from abc import ABCMeta, abstractmethod |
6
|
1 |
|
from time import sleep |
7
|
|
|
|
8
|
1 |
|
logger = logging.getLogger(__name__) |
9
|
|
|
|
10
|
|
|
# # Create handlers |
11
|
|
|
# c_handler = logging.StreamHandler() |
12
|
|
|
# f_handler = logging.FileHandler('file.log') |
13
|
|
|
# c_handler.setLevel(logging.INFO) |
14
|
|
|
# f_handler.setLevel(logging.DEBUG) |
15
|
|
|
# |
16
|
|
|
# # Create formatters and add it to handlers |
17
|
|
|
# c_format = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') |
18
|
|
|
# f_format = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') |
19
|
|
|
# c_handler.setFormatter(c_format) |
20
|
|
|
# f_handler.setFormatter(f_format) |
21
|
|
|
# |
22
|
|
|
# # Add handlers to the logger |
23
|
|
|
# logger.addHandler(c_handler) |
24
|
|
|
# logger.addHandler(f_handler) |
25
|
|
|
|
26
|
|
|
|
27
|
|
|
|
28
|
1 |
|
class AbstractYoutubeDownloader(object): |
29
|
1 |
|
__metaclass__ = ABCMeta |
30
|
|
|
@abstractmethod |
31
|
|
|
def download(self, video_url, directory, **kwargs): |
32
|
|
|
raise NotImplementedError |
33
|
|
|
|
34
|
|
|
|
35
|
1 |
|
class AbstractYoutubeDL(AbstractYoutubeDownloader): |
36
|
1 |
|
update_command_args = ('sudo', 'python' '-m', 'pip', 'install', '--upgrade', 'youtube-dl') |
37
|
1 |
|
update_backend_command = ' '.join(update_command_args) |
38
|
|
|
|
39
|
1 |
|
already_up_to_date_reg = re.compile(r'python\d[\d.]*/(site-packages \(\d[\d.]*\))',) |
40
|
1 |
|
updated_reg = re.compile(r'Collecting [\w\-_]+==(\d[\d.]*)') |
41
|
|
|
|
42
|
1 |
|
def download(self, video_url, directory, **kwargs): |
43
|
|
|
raise NotImplementedError |
44
|
|
|
|
45
|
1 |
|
@classmethod |
46
|
|
|
def update_backend(cls): |
47
|
|
|
args = ['python', '-m', 'pip', 'install', '--user', '--upgrade', 'youtube-dl'] |
48
|
|
|
output = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE) |
49
|
|
|
stdout = str(output.stdout, encoding='utf-8') |
50
|
|
|
if output.returncode == 0: |
51
|
|
|
match = cls.requirement_dir_reg.search(stdout) |
52
|
|
|
if match: |
53
|
|
|
logger.info("Backend 'youtube-dl' already up-to-date in '{}'".format(match.group(1))) |
54
|
|
|
else: |
55
|
|
|
logger.info("Updated with command '{}' to version {}".format(' '.join(args), cls.updated_reg.search(stdout))) |
56
|
|
|
else: |
57
|
|
|
logging.error("Something not documented happened while attempting to update youtube_dl: {}".format(str(output.stderr, encoding='utf-8'))) |
58
|
|
|
|
59
|
|
|
|
60
|
1 |
|
class CMDYoutubeDownloader(AbstractYoutubeDL): |
61
|
1 |
|
_args = ['youtube-dl', '--extract-audio', '--audio-quality', '0', '--audio-format', 'mp3', '-o', '%(title)s.%(ext)s'] |
62
|
1 |
|
__instance = None |
63
|
|
|
|
64
|
1 |
|
def __new__(cls, *args, **kwargs): |
65
|
|
|
if not cls.__instance: |
66
|
|
|
cls.__instance = super(CMDYoutubeDownloader, cls).__new__(cls) |
67
|
|
|
return cls.__instance |
68
|
|
|
|
69
|
1 |
|
def download(self, video_url, directory, suppress_certificate_validation=False, **kwargs): |
70
|
|
|
self._download(video_url, directory, suppress_certificate_validation=suppress_certificate_validation) |
71
|
|
|
|
72
|
1 |
|
@classmethod |
73
|
|
|
def _download(cls, video_url, directory, **kwargs): |
74
|
|
|
template = kwargs.get('template', '%(title)s.%(ext)s') |
75
|
|
|
args = ['youtube-dl', '--extract-audio', '--audio-quality', '0', '--audio-format', 'mp3', '-o', '{}/{}'.format(directory, template), video_url] |
76
|
|
|
# If suppress HTTPS certificate validation |
77
|
|
|
if kwargs.get('suppress_certificate_validation', False): |
78
|
|
|
args.insert(1, '--no-check-certificate') |
79
|
|
|
logger.info("Executing '{}'".format(' '.join(args))) |
80
|
|
|
process = subprocess.Popen(args, stderr=subprocess.PIPE) # stdout gets streamed in terminal |
81
|
|
|
stdout, stderr = process.communicate() |
82
|
|
|
if process.returncode != 0: |
83
|
|
|
if 2 < sys.version_info[0]: |
84
|
|
|
stderr = str(stderr, encoding='utf-8') |
85
|
|
|
else: |
86
|
|
|
stderr = str(stderr) |
87
|
|
|
raise YoutubeDownloaderErrorFactory.create_from_stderr(stderr, video_url) |
88
|
|
|
|
89
|
1 |
|
def download_trials(self, video_url, directory, times=10, delay=1, **kwargs): |
90
|
|
|
i = 0 |
91
|
|
|
while i < times - 1: |
92
|
|
|
try: |
93
|
|
|
self.download(video_url, directory, **kwargs) |
94
|
|
|
return |
95
|
|
|
except TooManyRequestsError as e: |
96
|
|
|
logger.info(e) |
97
|
|
|
i += 1 |
98
|
|
|
sleep(delay) |
99
|
|
|
self.download(video_url, directory, **kwargs) |
100
|
|
|
|
101
|
|
|
|
102
|
1 |
|
class YoutubeDownloaderErrorFactory(object): |
103
|
1 |
|
@staticmethod |
104
|
|
|
def create_with_message(msg): |
105
|
|
|
return Exception(msg) |
106
|
|
|
|
107
|
1 |
|
@staticmethod |
108
|
|
|
def create_from_stderr(stderror, video_url): |
109
|
|
|
exception_classes = (TokenParameterNotInVideoInfoError, InvalidUrlError, UnavailableVideoError, TooManyRequestsError, CertificateVerificationError) |
110
|
|
|
for subclass in exception_classes: |
111
|
|
|
if subclass.reg.search(stderror): |
112
|
|
|
return subclass(video_url, stderror) |
113
|
|
|
s = "NOTE: None of the predesinged exceptions' regexs [{}] matched. Perhaps you want to derive a new subclass from AbstractYoutubeDownloaderError to account for this youtube-dl exception with string to parse <S>{}</S>'".format(', '.join(['"{}"'.format(_.reg) for _ in exception_classes]), stderror) |
114
|
|
|
return Exception(AbstractYoutubeDownloaderError(video_url, stderror)._msg + '\n' + s) |
115
|
|
|
|
116
|
|
|
|
117
|
|
|
#### EXCEPTIONS |
118
|
|
|
|
119
|
1 |
|
class AbstractYoutubeDownloaderError(object): |
120
|
1 |
|
__metaclass__ = ABCMeta |
121
|
|
|
|
122
|
1 |
|
def __init__(self, *args, **kwargs): |
123
|
|
|
super(AbstractYoutubeDownloaderError, self).__init__() |
124
|
|
|
if len(args) > 1: |
125
|
|
|
self.video_url = args[0] |
126
|
|
|
self.stderr = args[1] |
127
|
|
|
elif len(args) > 0: |
128
|
|
|
self.video_url = args[0] |
129
|
|
|
self._msg = "YoutubeDownloader generic error." |
130
|
|
|
self._short_msg = kwargs.get('msg') |
131
|
|
|
if args or 'msg' in kwargs: |
132
|
|
|
self._msg = '\n'.join([_ for _ in [kwargs.get('msg', ''), getattr(self, 'stderr', '')] if _]) |
133
|
|
|
|
134
|
|
|
|
135
|
1 |
|
class TokenParameterNotInVideoInfoError(Exception, AbstractYoutubeDownloaderError): |
136
|
|
|
"""Token error""" |
137
|
1 |
|
reg = re.compile('"token" parameter not in video info for unknown reason') |
138
|
|
|
|
139
|
1 |
|
def __init__(self, video_url, stderror): |
140
|
|
|
AbstractYoutubeDownloaderError.__init__(self, video_url, stderror) |
141
|
|
|
Exception.__init__(self, self._msg) |
142
|
|
|
|
143
|
1 |
|
class InvalidUrlError(Exception, AbstractYoutubeDownloaderError): |
144
|
|
|
"""Invalid url error""" |
145
|
1 |
|
reg = re.compile(r'is not a valid URL\.') |
146
|
|
|
|
147
|
1 |
|
def __init__(self, video_url, stderror): |
148
|
|
|
AbstractYoutubeDownloaderError.__init__(self, video_url, stderror, msg="Invalid url '{}'.".format(video_url)) |
149
|
|
|
Exception.__init__(self, self._short_msg) |
150
|
|
|
|
151
|
1 |
|
class UnavailableVideoError(Exception, AbstractYoutubeDownloaderError): |
152
|
|
|
"""Wrong url error""" |
153
|
1 |
|
reg = re.compile(r'ERROR: This video is unavailable\.') |
154
|
|
|
|
155
|
1 |
|
def __init__(self, video_url, stderror): |
156
|
|
|
AbstractYoutubeDownloaderError.__init__(self, video_url, stderror, msg="Unavailable video at '{}'.".format(video_url)) |
157
|
|
|
Exception.__init__(self, self._msg) |
158
|
|
|
|
159
|
1 |
|
class TooManyRequestsError(Exception, AbstractYoutubeDownloaderError): |
160
|
|
|
"""Too many requests (for youtube) to serve""" |
161
|
1 |
|
reg = re.compile(r"(?:ERROR: Unable to download webpage: HTTP Error 429: Too Many Requests|WARNING: unable to download video info webpage: HTTP Error 429)") |
162
|
|
|
|
163
|
1 |
|
def __init__(self, video_url, stderror): |
164
|
|
|
AbstractYoutubeDownloaderError.__init__(self, video_url, stderror, msg="Too many requests for youtube at the moment.".format(video_url)) |
165
|
|
|
Exception.__init__(self, self._msg) |
166
|
|
|
|
167
|
1 |
|
class CertificateVerificationError(Exception, AbstractYoutubeDownloaderError): |
168
|
|
|
"""This can happen when downloading is requested from a server like scrutinizer.io\n |
169
|
|
|
ERROR: Unable to download webpage: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get |
170
|
|
|
local issuer certificate (_ssl.c:1056)> (caused by URLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] |
171
|
|
|
certificate verify failed: unable to get local issuer certificate (_ssl.c:1056)'))) |
172
|
|
|
""" |
173
|
1 |
|
reg = re.compile(r"ERROR: Unable to download webpage: <urlopen error \[SSL: CERTIFICATE_VERIFY_FAILED\]") |
174
|
|
|
|
175
|
1 |
|
def __init__(self, video_url, stderror): |
176
|
|
|
AbstractYoutubeDownloaderError.__init__(self, video_url, stderror, |
177
|
|
|
msg="Unable to download webpage because ssl certificate verification failed:\n[SSL: CERTIFICATE_VERIFY_FAILED] certificate " |
178
|
|
|
"verify failed: unable to get local issuer certificate (_ssl.c:1056)> (caused by " |
179
|
|
|
"URLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: " |
180
|
|
|
"unable to get local issuer certificate (_ssl.c:1056)')))") |
181
|
|
|
Exception.__init__(self, self._msg) |
182
|
|
|
|