Created
April 10, 2018 14:19
-
-
Save lst15/7cf9922c1280c8ae4f57b4b70b20b1a1 to your computer and use it in GitHub Desktop.
gistminer.miner.gist.python
This file contains hidden or 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
| #LINHA 31: COLOCAR DIRETORIO ONDE SERA SALVO TODOS OS GISTCODE | |
| #LINHA 32: COLOCAR LINK NO QUAL SERA 'GISTADO' | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from threading import Thread | |
| class varGlobal(): | |
| nav = 0 | |
| def main(diretorioASalvar,linkGistProfile): | |
| varGlobal.nav += 1 | |
| gitProfile = requests.get(linkGistProfile + '?page=' + str(varGlobal.nav)) | |
| soup = BeautifulSoup(gitProfile.content, 'html.parser') | |
| while bool(soup.find('a', class_='link-overlay')) == True: | |
| for i in soup.find_all('a', class_='link-overlay'): | |
| soupIntern = BeautifulSoup(requests.get(i.get('href')).content,'html.parser') | |
| saveNote = open(diretorioASalvar + soupIntern.find('strong', class_='css-truncate-target').string.replace('.py', '').replace('.txt', '') + '.txt', 'w') | |
| print soupIntern.find('strong', class_='css-truncate-target').string | |
| internalLinkedRaw = soupIntern.find('a',class_='btn btn-sm').get('href').replace('archive', 'raw').replace('.zip', '') | |
| internalLinkedRaw = requests.get('https://gist.githubusercontent.com' + internalLinkedRaw) | |
| saveNote.write(internalLinkedRaw.content) | |
| saveNote.close | |
| varGlobal.nav += 1 | |
| gitProfile = requests.get(linkGistProfile + str(varGlobal.nav)) | |
| soup = BeautifulSoup(gitProfile.content, 'html.parser') | |
| print ('Certifique-se que o diretorio de arquivamento especificado esteja de acordo com sua escolha.') | |
| dir = 'C:/Users/Leandro/Desktop/teste/' | |
| linked = 'https://gist.github.com/fmasanori' | |
| if raw_input('[y/n] Iniciar / Sair\n') == 'y': | |
| for i in range(5): | |
| t = Thread(target=main, args=(dir, linked),) | |
| t.start() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment