半次元无水印下载-Python
import requests
import json
import re
import os
import threading

def Requests(url):
    head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400'}
    n = 0
    while True:
        n += 1
        try:
            response = requests.get(url,headers = head,timeout = 10)
        except:
            pass
        else:
            if response.status_code == 200:
                return response
            if n >= 10:
                return False


def folder_mkdir():
    if os.path.exists(os.getcwd()+'\\pic'):
        pass
    else:
        os.mkdir(os.getcwd()+'\\pic')

    folder = os.getcwd()+'\\pic\\'

    return folder


def install_img(url,folder,name):
    try:
        img_content = Requests(url).content
    except:
        print('错误:{}     名称:{}'.fomat(url,name))
    else:
        open(folder+name,'wb').write(img_content)



def get_data(item_host_url):
    mode = 'thread'  #多线程下载模式
    folder = folder_mkdir()
    item_response = Requests(item_host_url)
    if item_response == False:
        return
    item_response.encoding = 'utf-8'
    try:
        item_data = re.findall('window.__ssr_data = JSON.parse\("(.*?)"\);\n      window._UID_ = \'0\';',item_response.text)[0].replace('\\"','"').replace('u002F','').replace('\\\\','/')
    except:
        pass
    else:
        item_img_data = json.loads(item_data,strict=False)['detail']['post_data']['multi']
        num = len(os.listdir(folder))
        print(num)
        for img_data in item_img_data:
            img_url = img_data['original_path']
            if img_url.find('jpg') >= 0:
                img_fomat = '.jpg'
            elif img_url.find('png') >= 0:
                img_fomat = '.png'
            else:
                img_fomat = '.jpg'

            num += 1
            name = str(num)+img_fomat
            if mode == 'thread':
                t = threading.Thread(target = install_img,args = (img_url,folder,name)).start()
                while True:
                    if len(threading.enumerate()) <= 25:
                        break
            else:
                install_img(img_url,folder,name)

if __name__ == '__main__':
    item_host_url = 'https://bcy.net/item/detail/6781452585363577870?_source_page=cos'
    get_data(item_host_url)
    print('下载完成')

Requests()

import requests
def Requests(url):
    head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400'}
    n = 0    #计算请求次数,错误过多则跳过此链接
    while True:
        n += 1
        try:
            response = requests.get(url,headers = head,timeout = 10)
        except:
            pass
        else:
            if response.status_code == 200:
                return response
            if n >= 10:
                return False

构建一个常用的请求模块,在错误时重新请求,超过一定请求次数后跳过

folder_mkdir()

import os
def folder_mkdir():
    if os.path.exists(os.getcwd()+'\\pic'):
        pass
    else:
        os.mkdir(os.getcwd()+'\\pic')

    folder = os.getcwd()+'\\pic\\'

    return folder

创建一个空文件夹用于储存图片

get_data()

def get_data(item_host_url):
    mode = 'thread'  #多线程下载模式
    folder = folder_mkdir()
    item_response = Requests(item_host_url)
    if item_response == False:
        return
    item_response.encoding = 'utf-8'
    try:
        item_data = re.findall('window.__ssr_data = JSON.parse\("(.*?)"\);\n      window._UID_ = \'0\';',item_response.text)[0].replace('\\"','"').replace('u002F','').replace('\\\\','/')
    except:
        pass
    else:
        item_img_data = json.loads(item_data,strict=False)['detail']['post_data']['multi']
        num = len(os.listdir(folder))
        print(num)
        for img_data in item_img_data:
            img_url = img_data['original_path']
            if img_url.find('jpg') >= 0:
                img_fomat = '.jpg'
            elif img_url.find('png') >= 0:
                img_fomat = '.png'
            else:
                img_fomat = '.jpg'

            num += 1
            name = str(num)+img_fomat
            if mode == 'thread':
                t = threading.Thread(target = install_img,args = (img_url,folder,name)).start()
                while True:
                    if len(threading.enumerate()) <= 25:
                        break
            else:
                install_img(img_url,folder,name)

请求图集链接,获取网页源码,从 <script> 标签中获取数据

半次元无水印下载-Python插图

我们对这的数据进行分析,发现这是一个json格式的数据,我先对这些数据进行处理,让python的json库可以解析它们。
我们可以看到,一些双引号(”)的前面都有反斜杠(\),这就导致json库无法解析这些数据

str.replace('\\"','"')

将在双引号前用于转义的反斜杠给去掉,这样数据解析就没有问题了。但是在这些数据中有一些没用的字块”u002F”

str.replace('u002F','')

到这一步数据的处理就基本完成了。不过只是这样还是不够的,因为其中用于储存图片的链接中的斜杠是反斜杠,用requests请求的时候无法识别,所以我们还需要将反斜杠转化成斜杠

str.replace('\\\\','/')

我们分析这些数据,发现图片链接在【detail【post_data【multi】】】的结构下
最终处理完的结果是这样的

半次元无水印下载-Python插图1

install_img()

def install_img(url,folder,name):
    try:
        img_content = Requests(url).content
    except:
        print('错误:{}     名称:{}'.fomat(url,name))
    else:
        open(folder+name,'wb').write(img_content)

传入三个属性,下载图片
构建下载函数是为了引进多线程下载的模式

通过while循环,获取线程数目加以限制,来防止线程过多导致被反。

while True:
    if len(threading.enumerate()) <= 25:
        break

枚举线程池中的线程数,如果大于25个就继续循环,阻塞主程序;小于25个则通过break跳出这一级的循环继续开线程下载图片。

暂无评论

发送评论 编辑评论


				
|´・ω・)ノ
ヾ(≧∇≦*)ゝ
(☆ω☆)
(╯‵□′)╯︵┴─┴
 ̄﹃ ̄
(/ω\)
∠( ᐛ 」∠)_
(๑•̀ㅁ•́ฅ)
→_→
୧(๑•̀⌄•́๑)૭
٩(ˊᗜˋ*)و
(ノ°ο°)ノ
(´இ皿இ`)
⌇●﹏●⌇
(ฅ´ω`ฅ)
(╯°A°)╯︵○○○
φ( ̄∇ ̄o)
ヾ(´・ ・`。)ノ"
( ง ᵒ̌皿ᵒ̌)ง⁼³₌₃
(ó﹏ò。)
Σ(っ °Д °;)っ
( ,,´・ω・)ノ"(´っω・`。)
╮(╯▽╰)╭
o(*////▽////*)q
>﹏<
( ๑´•ω•) "(ㆆᴗㆆ)
😂
😀
😅
😊
🙂
🙃
😌
😍
😘
😜
😝
😏
😒
🙄
😳
😡
😔
😫
😱
😭
💩
👻
🙌
🖕
👍
👫
👬
👭
🌚
🌝
🙈
💊
😶
🙏
🍦
🍉
😣
Source: github.com/k4yt3x/flowerhd
颜文字
Emoji
小恐龙
花!
上一篇
下一篇