zhasm
5/13/2013 - 10:58 AM

迅雷任务添加。 * 自动添加字符串中的可下载链接，例如 ed2k, magnet, thunder。 * 自动解析verycd 链接； * 支持递归解析（不常用） 需要 安装 requests 库。(sudo pip install requests; 或 su

迅雷任务添加。

  • 自动添加字符串中的可下载链接，例如 ed2k, magnet, thunder。
  • 自动解析verycd 链接；
  • 支持递归解析（不常用）

需要 安装 requests 库。(sudo pip install requests; 或 sudo easy_install requests)

默认的 离线迅雷代码库 在XL_PATH='python $HOME/git/lx/lixian_cli.py' 。如果跟你的路径不一样，请修改该变量。

xladd.py
content_copyfile_download
#!/usr/bin/env   python
# -*- encoding:  utf-8 -*-
#
#       Author:  Rex Zhang
#  Create Time:  2013-01-29 11:50
#    File name:  xladd.py

"""
usage:
xladd "string that contains downloadable resources, like ed2k, magnet, thunder."
xladd http://www.verycd.com/topics/2953431/
"""


import re
import os
import requests
from pprint import pprint

XL_PATH='python $HOME/git/lx/lixian_cli.py'

def getArgs():
    """show argpase snippets"""
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('links', nargs='+',
                        help='')

    parser.add_argument('-d', '--deep', action='store_false',
                        help='parse http to get links')
    return parser.parse_args()


def _deep_link(link):
    if link and 'http' in link.lower():
        deeper = False
        if 'verycd.com' in link.lower():
            deeper = True
            link = link.replace('verycd.com', 'verycd.gdajie.com')

        content = requests.get(link).content
        links = flatten_list(_parse_link(content, deep=False))

        if deeper :
            links = [_deep_link(i) for i in links if 'detail.htm' in i]

        links = flatten_list(links)
        links = [i for i in links if not i.lower().startswith('http')]

        return links

    else:
        return link


def _parse_link(link, deep=True):

    ret = []

    link_types = ['ed2k',
                  'magnet',
                  'thunder',
                  'http']

    types = '|'.join(link_types)
    regex_str = r'''(?i)(?:%s):[^"']{3,}''' % types

    regex = re.compile(regex_str)

    ret += regex.findall(link)

    if deep:
        ret = [_deep_link(r) for r in ret]
    return ret

def flatten_list(l):
    ret = []

    if not l:
        return []
    if not isinstance(l, list):
        return [l]

    for i in l:
        if not isinstance(i, list):
            ret.append(i)
        else:
            ret += flatten_list(i)
    return list(set(ret))

def get_links(args):
    ret = []
    for link in args.links:
        if '\n' in link:
            links = [i.strip() for i in link.splitlines()]
            for link in links:
                ret += _parse_link(link, args.deep)
        else:
            ret += _parse_link(link, args.deep)

    return flatten_list(ret)

def do(cmd):
    for i in os.popen(cmd).readlines():
        i = i.strip()
        if i:
            print i
    print

def add_task(links):
    for link in links:
        cmd = '''%(xl)s add "%(link)s"''' % {
            'xl': XL_PATH,
            'link': link,
            }
        do(cmd)

if __name__ == '__main__':
    args = getArgs()
    links = get_links(args)
    add_task(links)