漫画村

try:
    from bs4 import BeautifulSoup
except Exception as e:
    print "pip install beautifulsoup4"
    exit()
try:
    from selenium import webdriver
    from selenium.webdriver.firefox.options import Options
except Exception as e:
    print "pip install selenium"
    exit()
import time
import random
import re
import os

def sleep(interval=None):
    if interval == None:
        interval = random.uniform(0.5, 1.5)
    time.sleep(interval)

def run(target_url, is_show_gui=False):

    def _get_page_num(html):
        soup = BeautifulSoup(html, "html.parser")
        page_num = soup.find_all("a", href=re.compile("old_viewer"))[-1].text.strip()
        if page_num.isdigit():
            return int(page_num)
        else:
            print "err...could not get page number"
            exit()

    def _get_img_url(html):
        dl_list = []
        soup = BeautifulSoup(html, "html.parser")
        for img_url in soup.find_all("img", class_="miss", style="width:100%;"):
            if "imgon.spimg.ch" == img_url.get("src").split("/")[2]:
                dl_list.append(img_url.get("src"))
        return dl_list

    print "[+] Starting..."
    user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36"
    profile = webdriver.FirefoxProfile()
    profile.set_preference("general.useragent.override", user_agent)
    options = Options()
    if not is_show_gui:
        options.add_argument("--headless")
    driver = webdriver.Firefox(executable_path=r"I:/work/python/geckodriver/geckodriver.exe", firefox_profile=profile, firefox_options=options)

    driver.get(target_url)
    print "[+] Access -->", target_url
    sleep()

    viewer_url = target_url.split("?p=")[0] + "old_viewer?p=" + target_url.split("?p=")[1]
    driver.get(viewer_url)
    print "[+] Access -->", viewer_url
    sleep()

    save_path = target_url.split("?p=")[1]
    if not os.path.isdir(save_path):
        os.mkdir(save_path)
    print "[+] Create download folder. Save path -->", save_path

    page_num = _get_page_num(driver.page_source.encode("utf-8"))
    print "[+] Maximum number of pages -->", page_num
    sleep()

    for p in range(1, page_num+1):
        tmp_viewer_url = viewer_url + "&paged=%s" % p
        driver.get(tmp_viewer_url)
        print "[+] Access -->", tmp_viewer_url
        sleep()

        dl_list = _get_img_url(driver.page_source.encode("utf-8"))
        print "[+] Get images url. Number of images -->", len(dl_list)
        sleep()

        for img_url in dl_list:
            driver.get(img_url)
            save_file = save_path + "\\" + img_url.split("?")[0].split("/")[-1]
            with open(save_file, "wb") as file:
                file.write(driver.find_elements_by_tag_name("img")[0].screenshot_as_png)
            print "[-] Save img -->", img_url.split("?h")[0]
            sleep(interval=random.uniform(0.5, 1.0))

    print "[+] exit...bye"
    driver.quit()

def main():
    url = raw_input(prompt="Top page url of the book you want to download --> ")
    try:
        run(url)
    except Exception as e:
        print "err... -->", e
        exit()

if __name__ == '__main__':
    main()