File size: 2,865 Bytes
f399f41 |
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 |
from bs4 import BeautifulSoup
import requests
lang_ids = {
"Afrikaans": "af",
"Amharic": "am",
"Arabic": "ar",
"Asturian": "ast",
"Azerbaijani": "az",
"Bashkir": "ba",
"Belarusian": "be",
"Bulgarian": "bg",
"Bengali": "bn",
"Breton": "br",
"Bosnian": "bs",
"Catalan": "ca",
"Cebuano": "ceb",
"Czech": "cs",
"Welsh": "cy",
"Danish": "da",
"German": "de",
"Greeek": "el",
"English": "en",
"Spanish": "es",
"Estonian": "et",
"Persian": "fa",
"Fulah": "ff",
"Finnish": "fi",
"French": "fr",
"Western Frisian": "fy",
"Irish": "ga",
"Gaelic": "gd",
"Galician": "gl",
"Gujarati": "gu",
"Hausa": "ha",
"Hebrew": "he",
"Hindi": "hi",
"Croatian": "hr",
"Haitian": "ht",
"Hungarian": "hu",
"Armenian": "hy",
"Indonesian": "id",
"Igbo": "ig",
"Iloko": "ilo",
"Icelandic": "is",
"Italian": "it",
"Japanese": "ja",
"Javanese": "jv",
"Georgian": "ka",
"Kazakh": "kk",
"Central Khmer": "km",
"Kannada": "kn",
"Korean": "ko",
"Luxembourgish": "lb",
"Ganda": "lg",
"Lingala": "ln",
"Lao": "lo",
"Lithuanian": "lt",
"Latvian": "lv",
"Malagasy": "mg",
"Macedonian": "mk",
"Malayalam": "ml",
"Mongolian": "mn",
"Marathi": "mr",
"Malay": "ms",
"Burmese": "my",
"Nepali": "ne",
"Dutch": "nl",
"Norwegian": "no",
"Northern Sotho": "ns",
"Occitan": "oc",
"Oriya": "or",
"Panjabi": "pa",
"Polish": "pl",
"Pushto": "ps",
"Portuguese": "pt",
"Romanian": "ro",
"Russian": "ru",
"Sindhi": "sd",
"Sinhala": "si",
"Slovak": "sk",
"Slovenian": "sl",
"Somali": "so",
"Albanian": "sq",
"Serbian": "sr",
"Swati": "ss",
"Sundanese": "su",
"Swedish": "sv",
"Swahili": "sw",
"Tamil": "ta",
"Thai": "th",
"Tagalog": "tl",
"Tswana": "tn",
"Turkish": "tr",
"Ukrainian": "uk",
"Urdu": "ur",
"Uzbek": "uz",
"Vietnamese": "vi",
"Wolof": "wo",
"Xhosa": "xh",
"Yiddish": "yi",
"Yoruba": "yo",
"Chinese": "zh",
"Zulu": "zu",
}
def model_url_list():
url_list = []
for i in range(0, 5):
url_list.append(f"https://huggingface.co/models?other=m2m_100&p={i}&sort=downloads")
return url_list
def data_scraping():
url_list = model_url_list()
model_list = []
for url in url_list:
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
div_class = 'grid grid-cols-1 gap-5 2xl:grid-cols-2'
div = soup.find('div', {'class': div_class})
for a in div.find_all('a', href=True):
model_list.append(a['href'])
for i in range(len(model_list)):
model_list[i] = model_list[i][1:]
return model_list
|