Created
June 20, 2016 13:45
-
-
Save Pitasi/bc36bb30730325a1dbf8257d4c58767a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
url = 'http://www.tntvillage.scambioetico.org/src/releaselist.php' | |
categorie = [{"id":"0","nome":"Tutte le categorie"}, | |
{"id":"4","nome":"Film"}, | |
{"id":"2","nome":"Musica"}, | |
{"id":"29","nome":"Serie TV"}, | |
{"id":"14","nome":"Documentari"}, | |
{"id":"13","nome":"Students Releases"}, | |
{"id":"3","nome":"E Books"}, | |
{"id":"6","nome":"Linux"}, | |
{"id":"7","nome":"Anime"}, | |
{"id":"8","nome":"Cartoni"}, | |
{"id":"1","nome":"Programmi e Film TV"}, | |
{"id":"9","nome":"Macintosh"}, | |
{"id":"10","nome":"Windows Software"}, | |
{"id":"11","nome":"Pc Game"}, | |
{"id":"12","nome":"Playstation 2"}, | |
{"id":"21","nome":"Video Musicali"}, | |
{"id":"22","nome":"Sport"}, | |
{"id":"23","nome":"Teatro"}, | |
{"id":"24","nome":"Wrestling"}, | |
{"id":"25","nome":"Varie"}, | |
{"id":"26","nome":"Xbox"}, | |
{"id":"27","nome":"Immagini sfondi"}, | |
{"id":"28","nome":"Altri Giochi"}, | |
{"id":"30","nome":"Fumetteria"}, | |
{"id":"31","nome":"Trash"}, | |
{"id":"32","nome":"PlayStation 1"}, | |
{"id":"33","nome":"PSP Portable"}, | |
{"id":"34","nome":"Audiolibri"}, | |
{"id":"35","nome":"Podcast"}, | |
{"id":"36","nome":"Edicola"}, | |
{"id":"37","nome":"Mobile"}, | |
{"id":"38","nome":"Free Culture"}] | |
def parse_table(table): | |
if table is None: raise ValueError("table can't be none") | |
# Riga: | |
# 0: Torrent link | |
# 1: Magnet | |
# 2: Icona Categoria | |
# 3: Leechers | |
# 4: Seeders | |
# 5: Download Completati | |
# 6: Titolo | |
res = [] | |
for i in range(1, len(table)): | |
if len(table[i]) != 7: raise ValueError("invalid row: {}".format(r)) | |
tmp = {} | |
tmp['torrent'] = table[i][0].a['href'] if table[i][0].a['href'] != None else 'error' | |
tmp['magnet'] = table[i][1].a['href'] if table[i][0].a['href'] != None else 'error' | |
tmp['cat'] = table[i][2].img['src'] | |
tmp['l'] = int(table[i][3].string) | |
tmp['s'] = int(table[i][4].string) | |
tmp['c'] = int(table[i][5].string) | |
titolo = table[i][6].contents | |
if len(titolo) != 2: return [] | |
tmp['titolo'] = titolo[0].string.strip() | |
tmp['didascalia'] = titolo[1].string.strip() | |
res.append(tmp) | |
return res | |
def ricerca(query, cat=None, page=None): | |
params = { | |
'cat': cat, | |
'page': page, | |
'srcrel': query | |
} | |
r = requests.post(url, data = params) | |
if not r.ok: raise ConnectionError() | |
soup = BeautifulSoup(r.text, 'html.parser') | |
t = [] | |
for r in soup.find_all('tr'): | |
t.append(r.find_all('td')) | |
return parse_table(t) | |
def main(): | |
print("== Inserisci testo da cercare:") | |
query = input() | |
finished = False | |
while not finished: | |
print("== In quale categoria vuoi cercare? (Premi invio per visualizzare l'elenco.)") | |
cat = input() | |
if cat == "": | |
for i,c in enumerate(categorie): | |
print("{}={}, ".format(c['id'], c['nome'])) | |
else: finished = True | |
try: cat = int(cat) | |
except ValueError: | |
print("== Categoria non valida.") | |
exit(-1) | |
n = 1 | |
print("\n== Risultati per: {}".format(query)) | |
results = ricerca(query, cat=cat) | |
if len(results) == 0: | |
print("== Nessun risultato.") | |
exit(0) | |
for i,r in enumerate(results): | |
print("{}) {}\n {}{}".format(i+1, r['titolo'], "" if i < 9 else " ", r['didascalia'])) | |
print("== Digita il numero del torrent da selezionare:") | |
t = int(input()) - 1 | |
print("== Dettagli del torrent") | |
print("\n{}\n{}\n\nTorrent:\n{}".format(results[t]['titolo'], results[t]['didascalia'], results[t]['torrent'])) | |
return 0 | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment