SHOW:
|
|
- or go back to the newest paste.
| 1 | - | #Que os follen a todos corruptos hijos de la gran puta |
| 1 | + | #Que os follen a todos hijos de la gran puta |
| 2 | ||
| 3 | from urllib.request import urlopen | |
| 4 | from urllib.request import HTTPError | |
| 5 | ||
| 6 | print("START!")
| |
| 7 | ||
| 8 | robots_file = open("robots.txt",'r')
| |
| 9 | ||
| 10 | files_missing = [] | |
| 11 | files_total = 0 | |
| 12 | ||
| 13 | #For every line in robot | |
| 14 | for line in robots_file: | |
| 15 | ||
| 16 | #If it is a PDF file | |
| 17 | if ".pdf" in line: | |
| 18 | ||
| 19 | #Get the URL and name | |
| 20 | parts = line.split() | |
| 21 | url = 'http://boe.es'+parts[1] | |
| 22 | name_tree = parts[1].split('.pdf')[0].split('/')
| |
| 23 | name = name_tree[-1] | |
| 24 | ||
| 25 | #If is a SUM.pdf file, add also the date | |
| 26 | if name=="SUM": | |
| 27 | name = name + "_" + name_tree[3] + "_" + name_tree[4]+ "_" + name_tree[5] | |
| 28 | ||
| 29 | #Show what are you downloading | |
| 30 | print("downloading "+name+".pdf ... ")
| |
| 31 | ||
| 32 | #Download it | |
| 33 | try: | |
| 34 | f = urlopen(url) | |
| 35 | data = f.read() | |
| 36 | with open("pdfs/"+name+".pdf", "wb") as code:
| |
| 37 | code.write(data) | |
| 38 | except HTTPError: | |
| 39 | print("Can't download"+name+".pdf \n")
| |
| 40 | files_missing.append(name+".pdf") | |
| 41 | ||
| 42 | except URLError: | |
| 43 | print("Can't download"+name+".pdf \n")
| |
| 44 | print("Bad url "+url+" ¿? \n")
| |
| 45 | files_missing.append(name+".pdf") | |
| 46 | ||
| 47 | else: | |
| 48 | print("done! \n")
| |
| 49 | files_total = files_total + 1 | |
| 50 | ||
| 51 | ||
| 52 | print("Total Download = "+files_total)
| |
| 53 | print("Files not found = "+files_missing.size())
| |
| 54 | print("Files missing are...")
| |
| 55 | ||
| 56 | for element in files_missing: | |
| 57 | ||
| 58 | print(element) | |
| 59 | ||
| 60 | robots_file.close() |
