mirror of
https://github.com/vikstrous/pirate-get
synced 2025-01-10 10:04:21 +01:00
Unclutter main function
Why was everything inside main()?
This commit is contained in:
Rnhmjoj
parent
edc4d4ed71
commit
c823f1564e
458
pirate-get.py
458
pirate-get.py
@ -32,107 +32,7 @@ import urllib.request as request
|
||||
import urllib.parse as parse
|
||||
|
||||
from html.parser import HTMLParser
|
||||
from pprint import pprint
|
||||
from io import StringIO, BytesIO
|
||||
|
||||
|
||||
class NoRedirection(request.HTTPErrorProcessor):
|
||||
def http_response(self, request, response):
|
||||
return response
|
||||
|
||||
https_response = http_response
|
||||
|
||||
# create a subclass and override the handler methods
|
||||
class MyHTMLParser(HTMLParser):
|
||||
title = ''
|
||||
q = ''
|
||||
state = 'looking'
|
||||
results = []
|
||||
|
||||
def __init__(self, q):
|
||||
HTMLParser.__init__(self)
|
||||
self.q = q.lower()
|
||||
|
||||
def handle_starttag(self, tag, attrs):
|
||||
if tag == 'title':
|
||||
self.state = 'title'
|
||||
if tag == 'magnet' and self.state == 'matched':
|
||||
self.state = 'magnet'
|
||||
|
||||
def handle_data(self, data):
|
||||
if self.state == 'title':
|
||||
if data.lower().find(self.q) != -1:
|
||||
self.title = data
|
||||
self.state = 'matched'
|
||||
else:
|
||||
self.state = 'looking'
|
||||
if self.state == 'magnet':
|
||||
self.results.append([
|
||||
'magnet:?xt=urn:btih:' +
|
||||
parse.quote(data) +
|
||||
'&dn=' +
|
||||
parse.quote(self.title), '?', '?'])
|
||||
self.state = 'looking'
|
||||
|
||||
|
||||
def main():
|
||||
# new ConfigParser
|
||||
config = configparser.ConfigParser()
|
||||
|
||||
# default options so we dont die later
|
||||
config.add_section('SaveToFile')
|
||||
config.set('SaveToFile', 'enabled', 'false')
|
||||
config.set('SaveToFile', 'directory', '~/downloads/pirate-get/')
|
||||
|
||||
# load user options, to override default ones
|
||||
def config_to_load():
|
||||
if os.path.isfile(os.path.expandvars('$XDG_CONFIG_HOME/pirate-get')):
|
||||
return os.path.expandvars('$XDG_CONFIG_HOME/pirate-get')
|
||||
else:
|
||||
return os.path.expanduser('~/.config/pirate-get')
|
||||
|
||||
config.read([config_to_load()])
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
description='finds and downloads torrents from the Pirate Bay')
|
||||
parser.add_argument('-b', dest='browse',
|
||||
action='store_true',
|
||||
help="display in Browse mode")
|
||||
parser.add_argument('search', metavar='search',
|
||||
nargs="*", help="term to search for")
|
||||
parser.add_argument('-c', dest='category', metavar='category',
|
||||
help="specify a category to search", default="All")
|
||||
parser.add_argument('-s', dest='sort', metavar='sort',
|
||||
help="specify a sort option", default="SeedersDsc")
|
||||
parser.add_argument('-R', dest='recent', action='store_true',
|
||||
help="torrents uploaded in the last 48hours."
|
||||
"*ignored in searches*")
|
||||
parser.add_argument('-l', dest='list_categories',
|
||||
action='store_true',
|
||||
help="list categories")
|
||||
parser.add_argument('--list_sorts', dest='list_sorts',
|
||||
action='store_true',
|
||||
help="list Sortable Types")
|
||||
parser.add_argument('-t', dest='transmission',
|
||||
action='store_true',
|
||||
help="call transmission-remote to start the download")
|
||||
parser.add_argument('--custom', dest='command',
|
||||
help="call custom command, %%s will be replaced with"
|
||||
"the url")
|
||||
parser.add_argument('--local', dest='database',
|
||||
help="an xml file containing the Pirate Bay database")
|
||||
parser.add_argument('-p', dest='pages', default=1,
|
||||
help="the number of pages to fetch (doesn't work with"
|
||||
"--local)")
|
||||
parser.add_argument('-0', dest='first',
|
||||
action='store_true',
|
||||
help="choose the top result")
|
||||
parser.add_argument('-a', dest='download_all',
|
||||
action='store_true',
|
||||
help="download all results")
|
||||
parser.add_argument('--color', dest='color',
|
||||
action='store_false', default=True,
|
||||
help="disable colored output")
|
||||
from io import BytesIO
|
||||
|
||||
categories = {
|
||||
"All":"0",
|
||||
@ -196,6 +96,73 @@ def main():
|
||||
"CategoryDsc": "13", "CategoryAsc": "14",
|
||||
"Default": "99"}
|
||||
|
||||
|
||||
class NoRedirection(request.HTTPErrorProcessor):
|
||||
def http_response(self, request, response):
|
||||
return response
|
||||
|
||||
https_response = http_response
|
||||
|
||||
|
||||
# create a subclass and override the handler methods
|
||||
class MyHTMLParser(HTMLParser):
|
||||
title = ''
|
||||
q = ''
|
||||
state = 'looking'
|
||||
results = []
|
||||
|
||||
def __init__(self, q):
|
||||
HTMLParser.__init__(self)
|
||||
self.q = q.lower()
|
||||
|
||||
def handle_starttag(self, tag, attrs):
|
||||
if tag == 'title':
|
||||
self.state = 'title'
|
||||
if tag == 'magnet' and self.state == 'matched':
|
||||
self.state = 'magnet'
|
||||
|
||||
def handle_data(self, data):
|
||||
if self.state == 'title':
|
||||
if data.lower().find(self.q) != -1:
|
||||
self.title = data
|
||||
self.state = 'matched'
|
||||
else:
|
||||
self.state = 'looking'
|
||||
if self.state == 'magnet':
|
||||
self.results.append([
|
||||
'magnet:?xt=urn:btih:' +
|
||||
parse.quote(data) +
|
||||
'&dn=' +
|
||||
parse.quote(self.title), '?', '?'])
|
||||
self.state = 'looking'
|
||||
|
||||
|
||||
def print(*args, **kwargs):
|
||||
if kwargs.get('color', False):
|
||||
import colorama
|
||||
colorama.init()
|
||||
color_dict = {
|
||||
"default": "",
|
||||
"header": colorama.Back.BLACK + colorama.Fore.BLUE,
|
||||
"alt": colorama.Fore.YELLOW,
|
||||
"zebra_0": "",
|
||||
"zebra_1": colorama.Fore.BLUE,
|
||||
"WARN": colorama.Fore.MAGENTA,
|
||||
"ERROR": colorama.Fore.RED}
|
||||
|
||||
try:
|
||||
c = color_dict[kwargs.pop("color")]
|
||||
args = (c + args[0],) + args[1:] + (colorama.Style.RESET_ALL,)
|
||||
except KeyError as e:
|
||||
pass
|
||||
except IndexError as e:
|
||||
pass
|
||||
return builtins.print(*args, **kwargs)
|
||||
else:
|
||||
kwargs.pop('color', None)
|
||||
return builtins.print(*args, **kwargs)
|
||||
|
||||
|
||||
#todo: redo this with html parser instead of regex
|
||||
def remote(args, mirror):
|
||||
res_l = []
|
||||
@ -208,19 +175,19 @@ def main():
|
||||
"for the number of pages to fetch.")
|
||||
|
||||
if str(args.category) in categories.values():
|
||||
category = args.category;
|
||||
category = args.category
|
||||
elif args.category in categories.keys():
|
||||
category = categories[args.category]
|
||||
else:
|
||||
category = "0";
|
||||
category = "0"
|
||||
print("Invalid category ignored", color="WARN")
|
||||
|
||||
if str(args.sort) in sorts.values():
|
||||
sort = args.sort;
|
||||
sort = args.sort
|
||||
elif args.sort in sorts.keys():
|
||||
sort = sorts[args.sort]
|
||||
else:
|
||||
sort = "99";
|
||||
sort = "99"
|
||||
print("Invalid sort ignored", color="WARN")
|
||||
|
||||
# Catch the Ctrl-C exception and exit cleanly
|
||||
@ -253,11 +220,11 @@ def main():
|
||||
if f.info().get('Content-Encoding') == 'gzip':
|
||||
f = gzip.GzipFile(fileobj=BytesIO(f.read()))
|
||||
res = f.read().decode('utf-8')
|
||||
found = re.findall('"(magnet\:\?xt=[^"]*)|<td align="right">'
|
||||
'([^<]+)</td>', res)
|
||||
found = re.findall(r'"(magnet\:\?xt=[^"]*)|<td align="right">'
|
||||
r'([^<]+)</td>', res)
|
||||
|
||||
# check for a blocked mirror
|
||||
no_results = re.search("\"No hits\.", res)
|
||||
no_results = re.search(r"\"No hits\.", res)
|
||||
if found == [] and not no_results is None:
|
||||
# Contradiction - we found no results,
|
||||
# but the page didn't say there were no results.
|
||||
@ -267,12 +234,12 @@ def main():
|
||||
|
||||
# get sizes as well and substitute the character
|
||||
sizes.extend([match.replace(" ", " ")
|
||||
for match in re.findall("(?<=Size )[0-9.]"
|
||||
"+\ \;[KMGT]*[i ]*B", res)])
|
||||
for match in re.findall(r"(?<=Size )[0-9.]"
|
||||
r"+\ \;[KMGT]*[i ]*B", res)])
|
||||
|
||||
uploaded.extend([match.replace(" ", " ")
|
||||
for match in re.findall("(?<=Uploaded )"
|
||||
".+(?=\, Size)",res)])
|
||||
for match in re.findall(r"(?<=Uploaded )"
|
||||
r".+(?=\, Size)",res)])
|
||||
|
||||
identifiers.extend([match.replace(" ", " ")
|
||||
for match in re.findall("(?<=/torrent/)"
|
||||
@ -294,43 +261,11 @@ def main():
|
||||
curr = ['', 0, 0]
|
||||
except KeyboardInterrupt :
|
||||
print("\nCancelled.")
|
||||
exit()
|
||||
sys.exit(0)
|
||||
|
||||
# return the sizes in a spearate list
|
||||
return res_l, sizes, uploaded, identifiers
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
def make_print():
|
||||
if(args.color):
|
||||
import colorama
|
||||
colorama.init()
|
||||
color_dict = {
|
||||
"default": "",
|
||||
"header": colorama.Back.BLACK + colorama.Fore.BLUE,
|
||||
"zebra_0": "",
|
||||
"zebra_1": colorama.Fore.BLUE,
|
||||
"WARN": colorama.Fore.YELLOW,
|
||||
"ERROR": colorama.Fore.RED}
|
||||
|
||||
def n_print(*args, **kwargs):
|
||||
"""Print with colors"""
|
||||
try:
|
||||
c = color_dict[kwargs.pop("color")]
|
||||
args = (c + args[0],) + args[1:] + (colorama.Style.RESET_ALL,)
|
||||
except KeyError as e:
|
||||
pass
|
||||
except IndexError as e:
|
||||
pass
|
||||
return builtins.print(*args, **kwargs)
|
||||
else:
|
||||
def n_print(*args, **kwargs):
|
||||
if("color" in kwargs):
|
||||
kwargs.pop('color')
|
||||
return builtins.print(*args, **kwargs)
|
||||
return n_print
|
||||
|
||||
print=make_print()
|
||||
|
||||
def local(args):
|
||||
xml_str = ''
|
||||
@ -341,6 +276,151 @@ def main():
|
||||
return htmlparser.results
|
||||
|
||||
|
||||
# load user options, to override default ones
|
||||
def config_to_load():
|
||||
if os.path.isfile(os.path.expandvars('$XDG_CONFIG_HOME/pirate-get')):
|
||||
return os.path.expandvars('$XDG_CONFIG_HOME/pirate-get')
|
||||
else:
|
||||
return os.path.expanduser('~/.config/pirate-get')
|
||||
|
||||
|
||||
# enhanced print output with column titles
|
||||
def print_search_results(mags, sizes, uploaded):
|
||||
columns = int(os.popen('stty size', 'r').read().split()[1]) - 52
|
||||
cur_color = "zebra_0"
|
||||
|
||||
print("%5s %6s %6s %-5s %-11s %-11s %-*s" \
|
||||
% ( "LINK", "SEED", "LEECH", "RATIO", "SIZE", "UPLOAD", columns, "NAME"),
|
||||
color="header")
|
||||
|
||||
for m in range(len(mags)):
|
||||
magnet = mags[m]
|
||||
no_seeders = int(magnet[1])
|
||||
no_leechers = int(magnet[2])
|
||||
name = re.search(r"dn=([^\&]*)", magnet[0])
|
||||
|
||||
# compute the S/L ratio (Higher is better)
|
||||
try:
|
||||
ratio = no_seeders/no_leechers
|
||||
except ZeroDivisionError:
|
||||
ratio = 0
|
||||
|
||||
# Alternate between colors
|
||||
cur_color = "zebra_0" if (cur_color == "zebra_1") else "zebra_1"
|
||||
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
# enhanced print output with justified columns
|
||||
print("%5d %6d %6d %5.1f %-11s %-11s %-*s" % (
|
||||
m, no_seeders, no_leechers, ratio ,sizes[m],
|
||||
uploaded[m], columns, torrent_name), color=cur_color)
|
||||
|
||||
|
||||
def print_descriptions(chosen_links, mags, site, identifiers):
|
||||
for link in chosen_links:
|
||||
link = int(link)
|
||||
path = '/torrent/%s/' % identifiers[link]
|
||||
req = request.Request(site + path)
|
||||
req.add_header('Accept-encoding', 'gzip')
|
||||
f = request.urlopen(req)
|
||||
|
||||
if f.info().get('Content-Encoding') == 'gzip':
|
||||
f = gzip.GzipFile(fileobj=BytesIO(f.read()))
|
||||
|
||||
res = f.read().decode('utf-8')
|
||||
name = re.search(r"dn=([^\&]*)", mags[link][0])
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
desc = re.search(r"<div class=\"nfo\">\s*<pre>(.+?)(?=</pre>)",
|
||||
res, re.DOTALL).group(1)
|
||||
|
||||
# Replace HTML links with markdown style versions
|
||||
desc = re.sub(r"<a href=\"\s*([^\"]+?)\s*\"[^>]*>(\s*)([^<]+?)(\s*"
|
||||
r")</a>", r"\2[\3](\1)\4", desc)
|
||||
|
||||
print('Description for "' + torrent_name + '":', color="zebra_1")
|
||||
print(desc, color="zebra_0")
|
||||
|
||||
def print_fileLists(chosen_links, mags, site, identifiers):
|
||||
for link in chosen_links:
|
||||
path = '/ajax_details_filelist.php'
|
||||
query = '?id=' + identifiers[int(link)]
|
||||
req = request.Request(site + path + query)
|
||||
req.add_header('Accept-encoding', 'gzip')
|
||||
f = request.urlopen(req)
|
||||
|
||||
if f.info().get('Content-Encoding') == 'gzip':
|
||||
f = gzip.GzipFile(fileobj=BytesIO(f.read()))
|
||||
|
||||
res = f.read().decode('utf-8').replace(" ", " ")
|
||||
files = re.findall(r"<td align=\"left\">\s*([^<]+?)\s*</td><td ali"
|
||||
r"gn=\"right\">\s*([^<]+?)\s*</tr>", res)
|
||||
name = re.search(r"dn=([^\&]*)", mags[int(link)][0])
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
|
||||
print('Files in "' + torrent_name + '":', color="zebra_1")
|
||||
cur_color = "zebra_0"
|
||||
|
||||
for f in files:
|
||||
print("%-11s %s" % (f[1], f[0]), color=cur_color)
|
||||
cur_color = "zebra_0" if (cur_color == "zebra_1") else "zebra_1"
|
||||
|
||||
|
||||
def id_generator(size=6, chars=string.ascii_uppercase + string.digits):
|
||||
return ''.join(random.choice(chars) for _ in range(size))
|
||||
|
||||
|
||||
def main():
|
||||
# new ConfigParser
|
||||
config = configparser.ConfigParser()
|
||||
|
||||
# default options so we dont die later
|
||||
config.add_section('SaveToFile')
|
||||
config.set('SaveToFile', 'enabled', 'false')
|
||||
config.set('SaveToFile', 'directory', '~/downloads/pirate-get/')
|
||||
|
||||
config.read([config_to_load()])
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
description='finds and downloads torrents from the Pirate Bay')
|
||||
parser.add_argument('-b', dest='browse',
|
||||
action='store_true',
|
||||
help="display in Browse mode")
|
||||
parser.add_argument('search', metavar='search',
|
||||
nargs="*", help="term to search for")
|
||||
parser.add_argument('-c', dest='category', metavar='category',
|
||||
help="specify a category to search", default="All")
|
||||
parser.add_argument('-s', dest='sort', metavar='sort',
|
||||
help="specify a sort option", default="SeedersDsc")
|
||||
parser.add_argument('-R', dest='recent', action='store_true',
|
||||
help="torrents uploaded in the last 48hours."
|
||||
"*ignored in searches*")
|
||||
parser.add_argument('-l', dest='list_categories',
|
||||
action='store_true',
|
||||
help="list categories")
|
||||
parser.add_argument('--list_sorts', dest='list_sorts',
|
||||
action='store_true',
|
||||
help="list Sortable Types")
|
||||
parser.add_argument('-t', dest='transmission',
|
||||
action='store_true',
|
||||
help="call transmission-remote to start the download")
|
||||
parser.add_argument('--custom', dest='command',
|
||||
help="call custom command, %%s will be replaced with"
|
||||
"the url")
|
||||
parser.add_argument('--local', dest='database',
|
||||
help="an xml file containing the Pirate Bay database")
|
||||
parser.add_argument('-p', dest='pages', default=1,
|
||||
help="the number of pages to fetch (doesn't work with"
|
||||
"--local)")
|
||||
parser.add_argument('-0', dest='first',
|
||||
action='store_true',
|
||||
help="choose the top result")
|
||||
parser.add_argument('-a', dest='download_all',
|
||||
action='store_true',
|
||||
help="download all results")
|
||||
parser.add_argument('--color', dest='color',
|
||||
action='store_false', default=True,
|
||||
help="disable colored output")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.list_categories:
|
||||
cur_color = "zebra_0"
|
||||
for key, value in sorted(categories.iteritems()) :
|
||||
@ -381,85 +461,7 @@ def main():
|
||||
print("no results")
|
||||
return
|
||||
|
||||
# enhanced print output with column titles
|
||||
def print_search_results():
|
||||
columns = int(os.popen('stty size', 'r').read().split()[1]) - 52
|
||||
cur_color = "zebra_0"
|
||||
|
||||
print("%5s %6s %6s %-5s %-11s %-11s %-*s" \
|
||||
% ( "LINK", "SEED", "LEECH", "RATIO", "SIZE", "UPLOAD", columns, "NAME"),
|
||||
color="header")
|
||||
|
||||
for m in range(len(mags)):
|
||||
magnet = mags[m]
|
||||
no_seeders = int(magnet[1])
|
||||
no_leechers = int(magnet[2])
|
||||
name = re.search("dn=([^\&]*)", magnet[0])
|
||||
|
||||
# compute the S/L ratio (Higher is better)
|
||||
try:
|
||||
ratio = no_seeders/no_leechers
|
||||
except ZeroDivisionError:
|
||||
ratio = 0
|
||||
|
||||
# Alternate between colors
|
||||
cur_color = "zebra_0" if (cur_color == "zebra_1") else "zebra_1"
|
||||
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
# enhanced print output with justified columns
|
||||
print("%5d %6d %6d %5.1f %-11s %-11s %-*s" % (
|
||||
m, no_seeders, no_leechers, ratio ,sizes[m],
|
||||
uploaded[m], columns, torrent_name), color=cur_color)
|
||||
|
||||
def print_descriptions(chosen_links):
|
||||
for link in chosen_links:
|
||||
link = int(link)
|
||||
path = '/torrent/%s/' % identifiers[link]
|
||||
req = request.Request(mirror + path)
|
||||
req.add_header('Accept-encoding', 'gzip')
|
||||
f = request.urlopen(req)
|
||||
|
||||
if f.info().get('Content-Encoding') == 'gzip':
|
||||
f = gzip.GzipFile(fileobj=BytesIO(f.read()))
|
||||
|
||||
res = f.read().decode('utf-8')
|
||||
name = re.search("dn=([^\&]*)", mags[link][0])
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
desc = re.search(r"<div class=\"nfo\">\s*<pre>(.+?)(?=</pre>)",
|
||||
res, re.DOTALL).group(1)
|
||||
|
||||
# Replace HTML links with markdown style versions
|
||||
desc = re.sub(r"<a href=\"\s*([^\"]+?)\s*\"[^>]*>(\s*)([^<]+?)(\s*"
|
||||
r")</a>", r"\2[\3](\1)\4", desc)
|
||||
|
||||
print('Description for "' + torrent_name + '":', color="zebra_1")
|
||||
print(desc, color="zebra_0")
|
||||
|
||||
def print_fileLists(chosen_links):
|
||||
for link in chosen_links:
|
||||
path = '/ajax_details_filelist.php'
|
||||
query = '?id=' + identifiers[int(link)]
|
||||
req = request.Request(mirror + path + query)
|
||||
req.add_header('Accept-encoding', 'gzip')
|
||||
f = request.urlopen(req)
|
||||
|
||||
if f.info().get('Content-Encoding') == 'gzip':
|
||||
f = gzip.GzipFile(fileobj=BytesIO(f.read()))
|
||||
|
||||
res = f.read().decode('utf-8').replace(" ", " ")
|
||||
files = re.findall(r"<td align=\"left\">\s*([^<]+?)\s*</td><td ali"
|
||||
r"gn=\"right\">\s*([^<]+?)\s*</tr>", res)
|
||||
name = re.search("dn=([^\&]*)", mags[int(link)][0])
|
||||
torrent_name = parse.unquote(name.group(1)).replace("+", " ")
|
||||
|
||||
print('Files in "' + torrent_name + '":', color="zebra_1")
|
||||
cur_color = "zebra_0"
|
||||
|
||||
for f in files:
|
||||
print("%-11s %s" % (f[1], f[0]), color=cur_color)
|
||||
cur_color = "zebra_0" if (cur_color == "zebra_1") else "zebra_1"
|
||||
|
||||
print_search_results()
|
||||
print_search_results(mags, sizes, uploaded)
|
||||
|
||||
if args.first:
|
||||
print("Choosing first result");
|
||||
@ -506,11 +508,11 @@ def main():
|
||||
print("User Cancelled.")
|
||||
sys.exit(0)
|
||||
elif code == 'd':
|
||||
print_descriptions(choices)
|
||||
print_descriptions(choices, mags, site, identifiers)
|
||||
elif code == 'f':
|
||||
print_fileLists(choices)
|
||||
print_fileLists(choices, mags, site, identifiers)
|
||||
elif code == 'p':
|
||||
print_search_results()
|
||||
print_search_results(mags, sizes, uploaded)
|
||||
elif not l:
|
||||
print('No links entered!')
|
||||
else:
|
||||
@ -550,8 +552,6 @@ def main():
|
||||
else:
|
||||
webbrowser.open(url)
|
||||
|
||||
def id_generator(size=6, chars=string.ascii_uppercase + string.digits):
|
||||
return ''.join(random.choice(chars) for _ in range(size))
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Loading…
Reference in New Issue
Block a user