介绍

现在，樱花动漫上广告（色情）非常多，借助下面的代码就可以让我们在命令行中下载动漫，然后在本地进行观看。

下载的视频文件默认保存在代码所在目录下的animations/animation_name/episode_number.mp4。其中 animation_name 是动漫的全名，episode_number 是对应的集数。

代码

代码其实很好懂，就不写详细的注释了。不过，最好就着樱花动漫网站的源码食用，否则不可能看得懂，不过真的有人会仔细看嘛？（笑）

from urllib.parse import quote
from bs4 import BeautifulSoup
import requests
import re
import json
import os


REQUEST_TIMEOUT = 20
DOWNLOAD_CHUNK_SIZE = 1024 * 1024


class Animation(object):
    def __init__(self, a):
        self.title = a['title']
        self.number = a['href'].replace('/view/', '').replace('.html', '')


def getAnimationList(searchRequest):
    soup = BeautifulSoup(searchRequest.content.decode("gbk").encode("utf-8"), 'html.parser')
    divs = soup.find_all('div', attrs={'class': 'pics'})
    assert len(divs) == 2, '无法获取动漫列表！'
    return [Animation(li.h2.a) for li in divs[0].ul.find_all('li')]


def selectAnimation(animationList):
    animationCount = len(animationList)
    assert animationCount > 0, "未找到动漫"

    for i in range(animationCount):
        print(f"{i + 1}.{animationList[i].title}")

    index = -1
    while index >= animationCount or index < 0:
        try:
            index = int(input('选择一个: ')) - 1
        except:
            continue
    return animationList[index]


def getEpisodeList(animation):
    r = requests.get(f'http://www.imomoe.in/player/{animation.number}-0-0.html', timeout=REQUEST_TIMEOUT)
    match = re.search(r'"(/playdata/(\d+)/(\d+)(\.)js(\?)(\d+)(\.)(\d+))"', r.content.decode("gbk"))
    assert match, '无法获取集数列表地址！'

    r = requests.get('http://www.imomoe.in' + match.group(1), timeout=REQUEST_TIMEOUT)
    assert r, '无法获取集数列表！'

    js = re.sub(r",urlinfo='http://'\+document.domain\+'/player/(\d+)-<from>-<pos>.html';", "", r.content.decode("gbk")
            .replace('var VideoListJson=', '')).replace("'", '"')  # !转成合法json
    return json.loads(js)[0][1]


def selectEpisodes(episodeList):
    episodeCount = len(episodeList)
    assert episodeCount > 0, "未找到任何一集"

    print(f'共{episodeCount}集')

    while True:
        inputText = input('选择下载集数（多个使用单个空格分隔，输入"all"下载全部）：')
        if inputText.strip().lower() == 'all':
            return range(episodeCount)
        try:
            return [(int(i) - 1) for i in inputText.split(' ')]
        except:
            continue


def processBar(percent, startText='', endText='100%', totalLength=30):
    bar = ''.join(["#"] * int(percent * totalLength)) + ''
    bar = '\r' + startText + bar.ljust(totalLength) + ' {:0>4.1f}%|'.format(percent * 100) + endText
    print(bar, end='', flush=True)


def downloadVideo(url, path):
    r = requests.get(url, stream=True, timeout=REQUEST_TIMEOUT)
    assert r.ok, r.reason

    contentLength = len(r.content)
    print(f"文件大小：{contentLength}")

    downloadedLength = 0.0
    with open(path, "wb") as mp4:
        for chunk in r.iter_content(chunk_size=DOWNLOAD_CHUNK_SIZE):
            if chunk:
                mp4.write(chunk)
                downloadedLength += len(chunk)
                processBar(downloadedLength / contentLength)
        print()


if __name__ == '__main__':
    searchWord = quote(input('搜索: ').encode('gb2312'))
    searchRequest = requests.get('http://www.imomoe.in/search.asp?searchword=' + searchWord, timeout=REQUEST_TIMEOUT)
    animationList = getAnimationList(searchRequest)
    animation = selectAnimation(animationList)
    episodeList = getEpisodeList(animation)
    episodeIndices = selectEpisodes(episodeList)

    directory = os.path.join(os.path.dirname(__file__), 'animations', animation.title)
    if not os.path.exists(directory):
        os.makedirs(directory)

    print()

    for i in episodeIndices:
        print(f'开始下载第{i + 1}集')
        try:
            if i >= len(episodeList) or i < 0:
                raise ValueError()

            downloadVideo(episodeList[i].split('$')[1], os.path.join(directory, str(i + 1) + '.mp4').strip())
            print('下载成功')
        except Exception as e:
            print(e)
            print('下载失败')
        print()

    os.system('pause')