LOL爬蟲小工具

LOL爬蟲小工具是一款利用python指定爬取LOL高清壁紙、皮膚圖片、頭像圖片、圖標(biāo)等下載工具，根據(jù)網(wǎng)上的爬蟲教程結(jié)合愛好寫了個(gè)爬蟲，能爬取LOL國服官網(wǎng)資料庫里的圖片。研究了一下python,寫出了這么個(gè)小東西。

軟件說明

爬取英雄聯(lián)盟高清圖片

運(yùn)行結(jié)果

工具源碼

# coding=utf-8

import requests

import re

import json

import os

import urllib

import time

import threading  

from queue import Queue  

def getHttpStatusCode(url):

    try:

        request = requests.get(url)

        httpStatusCode = request.status_code

        return httpStatusCode

    except requests.exceptions.HTTPError as e:

        return e

def Get_Hero_Jsurl(queue):

    url = 'https://lol.qq.com/biz/hero/champion.js'

    response = requests.get(url).content.decode('gb2312')

    regular = r'data":(.*?),"version":"'

    dict_js = json.loads(re.findall(regular, response)[0])

    for _item in dict_js:

        EN = dict_js[_item]['id']

        queue.put(EN.format(id=_item))

def Stitching_JS_links(name_en):

    link = 'https://lol.qq.com/biz/hero/{}.js'.format(name_en)

    return link

def Parsing_hero_JS(url):

    response = requests.get(url).content.decode('gb2312')

    regular = r'data":(.*?),"version":"'

    js_data = json.loads(re.findall(regular, response)[0])

    result = {

        'name_CN': js_data['name'] + ' ' + js_data['title'],

        'name_EN': js_data['id'],

        'skins': js_data['skins'],

        'skill': js_data['spells'],

        'passive': js_data['passive'],

    }

    return result

def Download_hero_resources(detail_url_list: Queue, id):

    while len(detail_url_list.queue):

        hero_name = detail_url_list.get()

        Metadata = Parsing_hero_JS(Stitching_JS_links(hero_name))

        path = os.getcwd() + '\\英雄相關(guān)\\' + Metadata['name_CN']

        if not os.path.exists(path + '\\頭像'):

            os.makedirs(path + '\\頭像')

        if not os.path.exists(path + '\\皮膚'):

            os.makedirs(path + '\\皮膚')

        if not os.path.exists(path + '\\技能'):

            os.makedirs(path + '\\技能')

        # 下載皮膚和頭像圖  [img]https://game.gtimg.cn/images/lol/act/img/skin/big1000.jpg[/img]

        for item_skin in Metadata['skins']:

            url_0 = 'https://game.gtimg.cn/images/lol/act/img/skin/big{}.jpg'.format(

                item_skin['id'])

            url_1 = 'https://game.gtimg.cn/images/lol/act/img/skin/small{}.jpg'.format(

                item_skin['id'])

            urllib.request.urlretrieve(

                url_0,

                path + '\\皮膚\\' + item_skin['name'].replace('/', '') + '.jpg')

            urllib.request.urlretrieve(

                url_1,

                path + '\\頭像\\' + item_skin['name'].replace('/', '') + '.jpg')

            pass

        # 下載技能圖  [img]https://game.gtimg.cn/images/lol/act/img/spell/AnnieR.png[/img]

        for item_skill in Metadata['skill']:

            url_3 = 'https://game.gtimg.cn/images/lol/act/img/spell/{}.png'.format(

                item_skill['id'])

            save_path = path + '\\技能\\' + item_skill[

                'name'] + '_' + item_skill['id'].replace(hero_name,

                                                         '') + '.png'

            if (getHttpStatusCode(url_3) != 404):

                urllib.request.urlretrieve(url_3, save_path.replace('/', '-'))

        url_3 = 'https://game.gtimg.cn/images/lol/act/img/passive/{}'.format(

            Metadata['passive']['image']['full'])

        if (getHttpStatusCode(url_3) == 404):

            url_3 = 'https://game.gtimg.cn/images/lol/act/img/spell/{}'.format(

                Metadata['passive']['image']['full'])

        save_path = path + '\\技能\\' + Metadata['passive'][

            'name'] + '_P' + '.png'

        # test = getHttpStatusCode(url_3)

        urllib.request.urlretrieve(url_3, save_path.replace('/', '-'))

def Features_1():

    detail_url_queue = Queue(maxsize=1000)

    thread = threading.Thread(target=Get_Hero_Jsurl, args=(detail_url_queue, ))

    html_thread = []

    thread.start()

    for i in range(20):

        thread2 = threading.Thread(target=Download_hero_resources,

                                   args=(detail_url_queue, i))

        html_thread.append(thread2)

    start_time = time.time()

    print('將在2秒后啟動多線程下載')

    time.sleep(2)

    for i in range(20):

        html_thread[i].start()

    sum_num = len(detail_url_queue.queue)

    thread.join()

    for i in range(20):

        html_thread[i].join()

    time_ = time.time() - start_time

    print('共下載了{(lán)}位英雄資源'.format(sum_num))

    print("用時(shí): {}分{}秒".format(int(time_ // 60), int(time_ % 60) + 1))

def Features_2():

    hero_js = 'https://lol.qq.com/biz/hero/item.js'

    response = requests.get(hero_js).content.decode('gb2312')

    正則 = r'data":(.*?),"tree'

    list_js = re.findall(正則, response)

    dict_js = json.loads(list_js[0])

    Item_name = {}

    Item_url = {}

    if not os.path.exists(os.getcwd() + '\\裝備'):

        os.makedirs(os.getcwd() + '\\裝備')

    for i in dict_js:

        Item_name[i] = dict_js[i]['name']

        url0 = 'https://game.gtimg.cn/images/lol/act/img/item/'

        url1 = '.png'

        Item_url[i] = url0 + i + url1

    p = 0

    for i in Item_url:

        urllib.request.urlretrieve(

            Item_url[i],

            os.getcwd() + '\\裝備\\' + Item_name[i] + '.png')

        p += 1

        _JD = (p / len(Item_url)) * 100

        print('已完成 ', end='')

        print('%.2lf' % _JD, end=' %\n')

def main():

    print('LOL爬蟲小工具 作者:艾斯托維亞')

    print('———————————————————————————————————————')

    print(' 1 |  從官網(wǎng)下載最新英雄頭像、皮膚原畫、技能圖標(biāo)')

    print(' 2 |    從官網(wǎng)下載最新最新裝備圖    ')

    print('———————————————————————————————————————')

    n = input('請輸入數(shù)字以選擇功能\n')

    n = int(n)

    if n > 0 and n < 3:

        swicth = {

            1: Features_1,

            2: Features_2,

        }

        swicth[n]()

        input('數(shù)據(jù)保存在軟件同目錄\n按任意鍵退出\n')

    else:

        print('錯(cuò)誤輸入\n程序即將退出')

        time.sleep(2)

if __name__ == "__main__":

    main()