Download archives from http://www.tuku.cc/

cctuku.py

# coding=utf-8

import os
import re
import sys
import zipfile
import requests

# Your cookie
headers = {'Cookie': 'your cookie'}


def ensure_dir(directory):
    if not os.path.exists(directory):
        os.makedirs(directory)


def print_same_line(string):
    sys.stdout.write('\r%s' % string)
    sys.stdout.flush()


# http://stackoverflow.com/questions/16694907/how-to-download-large-file-in-python-with-requests-py
def download_file(url, local_file):
    r = requests.get(url, stream=True)
    content_length = r.headers.get('Content-Length')
    if content_length:
        size = int(content_length)
    else:
        size = -1
    downloaded = 0
    if size != -1:
        print_same_line('0.00%')
    with open(local_file, 'wb') as f:
        for chunk in r.iter_content(chunk_size=1024):
            if chunk:  # filter out keep-alive new chunks
                f.write(chunk)
                f.flush()
                downloaded += len(chunk)
                if size != -1:
                    print_same_line('%.2f%%' % (downloaded * 100 / float(size)))
    if size != -1:
        print


def get_download_url(part_url):
    r = requests.get(part_url, headers=headers)
    p = re.compile(r'var downurl = Tk\.jsonp_url\+"([^"]+)"')
    m = p.search(r.content)
    another_url = 'http://rtk.um5.cc/' + m.group(1)
    r = requests.get(another_url, headers=headers)
    p = re.compile(r'\("<a href=\\"([^"]+)\\"')
    m = p.search(r.content.replace('\/', '/'))
    return m.group(1)


def get_download_url_list(comic_url):
    r = requests.get(comic_url)
    p = re.compile(r'<li class="current"><h1>([^<]+)</h1></li>')
    m = p.search(r.content)
    name = ''.join(c for c in m.group(1).decode('utf-8').encode('gbk') if c not in ('\\', '/', ':', '*', '?', '"', '<', '>', '|')).rstrip()

    p = re.compile(r'<a href="([^"]+)" title=".+?">下载</a>')

    l = []
    for m in p.finditer(r.content):
        l.append('http://www.tuku.cc' + m.group(1))

    # The newest part is on the top, so reverse the list
    l.reverse()
    return name, l


# Sometimes download failed, the zip file is broken
def test_zip(zip_file_path):
    try:
        zipfile.ZipFile(zip_file_path)
        return True
    except (zipfile.BadZipfile):
        print '*~*~*~*~*~*~*~*~ Warning Bad Zip File ~*~*~*~*~*~*~*~*'
        os.remove(zip_file_path)
        return False


def download_comic(comic_url):
    download_dir, part_url_list = get_download_url_list(comic_url)
    ensure_dir(download_dir)
    error_times = 0
    i = 0
    for part_url in part_url_list:
        i += 1
        print '### Part', i
        print '* Part Url', part_url

        file_name = '%04d.zip' % i
        print '* File Name', file_name
        file_path = os.path.join(download_dir, file_name)
        print '* File Path', file_path

        # Check exists
        if os.path.exists(file_path) and test_zip(file_path):
            print '* Exists', file_name
            continue

        file_url = get_download_url(part_url)
        print '* File Url', file_url

        download_file(file_url, file_path)

        if not test_zip(file_path):
            print '* Part %d Download Failed' % i
            error_times += 1
        else:
            print '* Part %d Download Complete' % i

    return error_times


def download_comic_completely(comic_url):
    turn = 1
    while True:
        print '## Turn', turn
        if not download_comic(comic_url):
            break
        else:
            turn += 1


def main():
    for url in sys.argv[1:]:
        print '# Start Comic', url
        download_comic_completely(url)
        print


if __name__ == "__main__":
    main()