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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
|
from youtube import common, channel
import settings
from string import Template
import sqlite3
import os
import secrets
import datetime
# so as to not completely break on people who have updated but don't know of new dependency
try:
import atoma
except ModuleNotFoundError:
print('Error: atoma not installed, subscriptions will not work')
with open('yt_subscriptions_template.html', 'r', encoding='utf-8') as f:
subscriptions_template = Template(f.read())
# https://stackabuse.com/a-sqlite-tutorial-with-python/
database_path = os.path.join(settings.data_dir, "subscriptions.sqlite")
def open_database():
if not os.path.exists(settings.data_dir):
os.makedirs(settings.data_dir)
connection = sqlite3.connect(database_path)
# Create tables if they don't exist
try:
cursor = connection.cursor()
cursor.execute('''CREATE TABLE IF NOT EXISTS subscribed_channels (
id integer PRIMARY KEY,
channel_id text NOT NULL,
channel_name text NOT NULL,
time_last_checked integer
)''')
cursor.execute('''CREATE TABLE IF NOT EXISTS videos (
id integer PRIMARY KEY,
uploader_id integer NOT NULL REFERENCES subscribed_channels(id) ON UPDATE CASCADE ON DELETE CASCADE,
video_id text NOT NULL,
title text NOT NULL,
duration text,
time_published integer NOT NULL,
description text
)''')
connection.commit()
except:
connection.rollback()
connection.close()
raise
return connection
def _subscribe(channel_id, channel_name):
connection = open_database()
try:
cursor = connection.cursor()
cursor.execute("INSERT INTO subscribed_channels (channel_id, name) VALUES (?, ?)", (channel_id, channel_name))
connection.commit()
except:
connection.rollback()
raise
finally:
connection.close()
def _unsubscribe(channel_id):
connection = open_database()
try:
cursor = connection.cursor()
cursor.execute("DELETE FROM subscribed_channels WHERE channel_id=?", (channel_id, ))
connection.commit()
except:
connection.rollback()
raise
finally:
connection.close()
def _get_videos(number, offset):
connection = open_database()
try:
cursor = connection.cursor()
db_videos = cursor.execute('''SELECT video_id, title, duration, channel_name
FROM videos
INNER JOIN subscribed_channels on videos.uploader_id = subscribed_channels.id
ORDER BY time_published DESC
LIMIT ? OFFSET ?''', (number, offset))
for db_video in db_videos:
yield {
'id': db_video[0],
'title': db_video[1],
'duration': db_video[2],
'author': db_video[3],
}
except:
connection.rollback()
raise
finally:
connection.close()
units = {
'year': 31536000, # 365*24*3600
'month': 2592000, # 30*24*3600
'week': 604800, # 7*24*3600
'day': 86400, # 24*3600
'hour': 3600,
'minute': 60,
'second': 1,
}
def youtube_timestamp_to_posix(dumb_timestamp):
''' Given a dumbed down timestamp such as 1 year ago, 3 hours ago,
approximates the unix time (seconds since 1/1/1970) '''
dumb_timestamp = dumb_timestamp.lower()
now = time.time()
if dumb_timestamp == "just now":
return now
split = dumb_timestamp.split(' ')
number, unit = int(split[0]), split[1]
if number > 1:
unit = unit[:-1] # remove s from end
return now - number*units[unit]
weekdays = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
months = ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec')
def _get_upstream_videos(channel_id, channel_name, time_last_checked):
feed_url = "https://www.youtube.com/feeds/videos.xml?channel_id=" + channel_id
headers = {}
# randomly change time_last_checked up to one day earlier to make tracking harder
time_last_checked = time_last_checked - secrets.randbelow(24*3600)
# If-Modified-Since header: https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/If-Modified-Since
struct_time = time.gmtime(time_last_checked)
weekday = weekdays[struct_time.tm_wday] # dumb requirement
month = months[struct_time.tm_mon - 1]
headers['If-Modified-Since'] = time.strftime(weekday + ', %d ' + month + ' %Y %H:%M:%S GMT', struct_time)
print(headers['If-Modified-Since'])
headers['User-Agent'] = 'Python-urllib' # Don't leak python version
headers['Accept-Encoding'] = 'gzip, br'
req = urllib.request.Request(url, headers=headers)
if settings.route_tor:
opener = urllib.request.build_opener(sockshandler.SocksiPyHandler(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 9150))
else:
opener = urllib.request.build_opener()
response = opener.open(req, timeout=15)
if response.getcode == '304':
print('No new videos for ' + channel_id)
return []
content = response.read()
print('Retrieved videos for ' + channel_id)
content = common.decode_content(content, response.getheader('Content-Encoding', default='identity'))
feed = atoma.parse_atom_bytes(content)
atom_videos = {}
for entry in feed.entries:
video_id = entry.id_[9:] # example of id_: yt:video:q6EoRBvdVPQ
# standard names used in this program for purposes of html templating
atom_videos[video_id] = {
'title': entry.title.value,
'author': entry.authors[0].name,
#'description': '', # Not supported by atoma
#'duration': '', # Youtube's atom feeds don't provide it.. very frustrating
'published': entry.published.strftime('%m/%d/%Y'),
'time_published': int(entry.published.timestamp()),
}
# final list
videos = []
# Now check channel page to retrieve missing information for videos
json_channel_videos = channel.get_grid_items(channel.get_channel_tab(channel_id)[1]['response'])
for json_video in json_channel_videos:
info = renderer_info(json_video)
if info['id'] in atom_videos:
info.update(atom_videos[info['id']])
else:
info['author'] = channel_name
info['time published'] = youtube_timestamp_to_posix(info['published'])
videos.append(info)
return videos
def get_subscriptions_page(env, start_response):
items_html = '''<nav class="item-grid">\n'''
for item in _get_videos(30, 0):
items_html += common.video_item_html(info, common.small_video_item_template)
items_html += '''\n</nav>'''
start_response('200 OK', [('Content-type','text/html'),])
return subscriptions_template.substitute(
header = common.get_header(),
items = items_html,
page_buttons = '',
).encode('utf-8')
|
