coding_project/main.py at main · Robert0622/coding_project · 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
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
import re
from pyyoutube import Api
import os
import csv
import urllib.request
import re
from videos import get_video_info, download_video, search_video, detect_background_change, divide_video
import openpyxl

api_key = "AIzaSyAK-BlzaRCnoDG6L0RbHp0spMT1htOEsV8"
api = Api(api_key=api_key)

NBA_channels = ['GoldenHoops',
'GDsHighlights', 'fingeroll_', 'TJCyt1', 'kingjetzz', 'SnapBackSports', 'Houseofhighlights', 'SwishCultures', 'NBAOnFire-', 'Jnglert']

basketball_youtuber_channels = ['JoshWalker5', 'braxtonpicou', 'dexton4'
 'Thesosorondo', 'RealJDub', 'ChrisStaplesDunker', 'seggie', 'R2bball', 'JumpmanJimmy', 'Maxisnicee', 'simonssaysjax']
basketball_youtuber_channels = ['afv']
basketball_podcasts = []

basketball_highlight_channels = ['PureSweat', 'OTEATL', 'killerjunior23', 'TristanJass', 'DunkademicsOfficial', 'R2bball', 'jlawbball7293', 'ChrisJohnsonHoops',
 'Overtime', 'Maxisnicee', 'EliteMixtapes', 'ShowtimeFilms', 'lakers' ]

anime_channels = ['AniMemes08', 'UzumakiMadara', 'animixed106', 'animeshorts2910', 'animeshorts3852', 'viisual_ice8016',
'SarotsiX', 'hokage_minato_shorts', 'CrunchyrollCollection', 'upsidedownart09', 'Animeme_TV', 'ouranimax8661']
#'NotSafe' 'janerijk4046'
game_channels = ['Daaninator', 'BaileysDad', 'TeamKSA', 'Crusher_21', '1st', 'DeekoShorts', 'GEVids', 'spy.animes',
    'MooseShorts', 'camman18', 'TwiShorts', 'BRAWLMAKER', 'minecraftnutiy', 'fvdge','hellfrozen9971',
    'theWizCR', 'ClashRoyaleTeam', 'royleplus2546']
#'bobdealanl'
music_channels = ['maxgrabel', 'muzicclout', 'JarredJermaine', 'ArcNorthDaily', 'LandenPurifoy']
def main(channel_type, number_of_vids, type, scene_cut):
    from videos import search_video
    with open(f'{channel_type}.csv', 'w') as f:
        f.truncate()
        writer = csv.writer(f)
        writer.writerow(['channel_name', 'title', 'thumbnail_url', 'tags', 'done?', 'uploaded?'])
        f.close()

    excel_path = f'/Users/Tiger/Desktop/videos_storage/{channel_type}.xlsx'
    book = openpyxl.load_workbook(excel_path)
    sheet = book['Sheet1']
    for row in sheet: remove(sheet,row)
    book.save(excel_path)

    if channel_type == 'NBA_channels': channels = NBA_channels
    elif channel_type == 'basketball_youtuber_channels': channels = basketball_youtuber_channels

    elif channel_type == 'basketball_highlight_channels': channels = basketball_highlight_channels
    elif channel_type == 'anime': channels = anime_channels
    else: pass

    shorts_collection = []
    for channel in channels:
        get_youtube_shorts(channel, api, shorts_collection, type)
        print('getting videos...')
    #print(shorts_collection)
    shorts_collection = (sorted(shorts_collection, key = lambda x : int(x[1]), reverse=True))[:number_of_vids]
    print(shorts_collection)
    download_shorts(shorts_collection, channel_type, api, type, scene_cut)

    search_video.convert_csv_to_excel(channel_type)

def get_youtube_shorts(channel_name, api, shorts_collection, type):
    page_url = 'https://www.youtube.com/@' + channel_name + f'/{type}'
    webUrl = urllib.request.urlopen(page_url)

    if type == 'shorts':
        new = re.findall(r'[/][s][h][o][r][t][s][/].+?["]', str(webUrl.read()))
        shorts_ids = []
        for item in new:
            if item != '/shorts/shorts"':
                shorts_ids.append(item[:-1])

        for shorts_id in shorts_ids:
            useful_info = get_video_info.get_useful_info(shorts_id[8:], api)
            publishedAt = useful_info['publishedAt']
            statistics = useful_info['statistics']
            #if search_video.check_update_by_time(publishedAt):
            if True:
                shorts_collection.append((shorts_id[8:], statistics, channel_name))

    else:
        new = re.findall(r'["][v][i][d][e][o][I][d][s]["][:][[]["](.+?)["]', str(webUrl.read()))
        videos_ids = []
        for item in new:
            if item not in videos_ids:
                videos_ids.append(item)

        for video_id in videos_ids:
            useful_info = get_video_info.get_useful_info(video_id, api)
            publishedAt = useful_info['publishedAt']
            statistics = useful_info['statistics']
            #if search_video.check_update_by_time(publishedAt):
            if True:
                shorts_collection.append((video_id, statistics, channel_name))


def download_shorts(shorts_collection, channel_type, api, type, scene_cut):
    with open(f'{channel_type}.csv', 'a', newline='') as f:
        writer = csv.writer(f)
        path = '/Users/Tiger/Desktop/videos_storage/'

        for i in range(len(shorts_collection)):
            shorts_id, channel_name = shorts_collection[i][0], shorts_collection[i][2]
            useful_info = get_video_info.get_useful_info(shorts_id, api)

            folder_name = f'{channel_type}/{str(i)}/'
            if type == 'shorts':
                link = 'https://www.youtube.com/shorts/' + shorts_id
            else:
                link = 'https://www.youtube.com/watch?v=' + shorts_id
            print(link)

            if scene_cut:
                download_video.download_yt_vid(path+folder_name, link, str(i))
                print('downloaded!')
                print(path+folder_name+title+'.mp4')

                print('dividing vids...')
                divide_video.simple_divide(path+folder_name+str(i), 0, 25)
            else:
                title = useful_info['title']
                thumbnail_url = useful_info['thumbnail_max']
                tags = useful_info['tags']
                download_video.download_yt_vid(path+folder_name, link, title)

                writer.writerow([channel_name, title, thumbnail_url, tags, ' ', ''])

                try:
                    download_video.download_image(thumbnail_url, path + folder_name, 'thumbnail.png')

                except: pass
    f.close()

def remove(sheet, row):
	# iterate the row object
	for cell in row:
		# check the value of each cell in
		# the row, if any of the value is not
		# None return without removing the row
		if cell.value != None:
			return
	# get the row number from the first cell
	# and remove the row
	sheet.delete_rows(row[0].row, 1)

main('basketball_youtuber_channels', 2, 'videos', True)


def motivational_speech(path):
    from audios import add_sub, get_sub, translate, txt_to_list
    from videos import download_video, search_video, get_video_info

    # download newest vid into video folder
    video_id = search_video.get_newest_video(channel_id, api)
    #sub = translate.get_subtitle(video_id, path_1)
    download_video.download_video(ytid = video_id, path = path, format = 'mp4')

    #translate video title
    title_eng = get_video_info.get_useful_info(video_id, api)['title']
    title_chi = translate.translate(title_eng)
    print(title_chi)

    ### need to work on naming
    get_sub(video_id, title_chi, path+'audios_storage')
    sub_txt_path = path + 'audios_storage' + title_chi + '.txt'
    sub_list = txt_to_list(sub_txt_path, [])