Python--快速爬取千张高清壁纸

最新推荐文章于 2024-04-04 01:26:19 发布

vigigo

最新推荐文章于 2024-04-04 01:26:19 发布

阅读量330

点赞数 1

分类专栏： python # reptile 文章标签： python 爬虫

本文链接：https://blog.csdn.net/qq_40574123/article/details/116466195

版权

python 同时被 2 个专栏收录

9 篇文章 1 订阅

订阅专栏

reptile

1 篇文章 0 订阅

订阅专栏

快速下载数百张高清壁纸

在这里插入图片描述

代码部分

import requests
from bs4 import BeautifulSoup
import os
import time
import random,codecs

import UserAgent


index = 'http://www.netbian.com' # 网站根地址
interval = 3 # 爬取图片的间隔时间
firstDir = 'F:\pituresque' # 总路径
classificationDict = {} # 存放网站分类子页面的信息
#通过选择器来获取页面项
def screen(url, select):
    html = requests.get(url = url, headers = UserAgent.get_headers()) # 随机获取一个headers
    html.encoding = 'gbk'
    html = html.text
    soup = BeautifulSoup(html, 'lxml')
    return soup.select(select)

# 获取页码
def screenPage(url, select):
    html = requests.get(url = url, headers = UserAgent.get_headers())
    html.encoding = 'gbk'
    html = html.text
    soup = BeautifulSoup(html, 'lxml')
    return soup.select(select)[0].next_sibling.text

# 将分类子页面信息存放在字典中
def init_classification():
    url = index
    select = '#header > div.head > ul > li:nth-child(1) > div > a'#可能需要修改div
    classifications = screen(url, select)
    for c in classifications:#div标签下面的每一个a标签
        href = c.get('href') # 获取的是相对地址
        text = c.string # 获取分类名title字段
        if(text == '4k壁纸'): # 4k壁纸，因权限问题无法爬取，直接跳过
            continue
        if (text != '美女'):
            continue
        secondDir = (firstDir + '/' + text).replace('\\','/') # 分类目录
        url = index + href # 分类子页面url
        global classificationDict
        classificationDict[text] = {
            'path': secondDir,#保存地址
            'url': url#爬取地址
        }

# 下载操作
def download(src, name, path):
    if(isinstance(src, str)):
        response = requests.get(src)
        if  not os.path.exists(path):
            os.mkdir(path)
        path = path + '/' + name + '.jpg'
        while(os.path.exists(path)): # 若文件名重复
            path = path.split(".")[0] + str(random.randint(2, 17)) + '.' + path.split(".")[1]
        with open(path,'wb') as pic:
            for chunk in response.iter_content(128):
                pic.write(chunk)

def handleImgs(links, path):#传入links就可以
    num = 0
    for link in links:
        href = link.get('href')
        if(href == 'http://pic.netbian.com/' or href == 'https://pic.netbian.com/'): # 过滤图片广告
            continue
        print(link)
        # 第一次跳转
        if('http://' in href): # 有极个别图片不提供正确的相对地址
            url = href
        else:
            url = index + href
        select = 'div#main div.endpage div.pic div.pic-down a'
        link = screen(url, select)
        if(link == []):
            print(url + ' 无此图片，爬取失败')
            continue
        href = link[0].get('href')

        # 第二次跳转
        url = index + href

        # 获取到图片了
        select = 'div#main table a img'
        link = screen(url, select)
        if(link == []):
            print(url + " 该图片需要登录才能爬取，爬取失败")
            continue
        name = link[0].get('alt').replace('\t', '').replace('|', '').replace(':', '').replace('\\', '').replace('/', '').replace('*', '').replace('?', '').replace('"', '').replace('<', '').replace('>', '')
        print(name) # 输出下载图片的文件名
        src = link[0].get('src')
        if(requests.get(src).status_code == 404):
            print(url + ' 该图片下载链接404，爬取失败')

            continue
        download(src, name, path)
        time.sleep(interval)
        num = num + 1
        print(num)


# search_url = 'http://www.netbian.com/e/sch/index.php?keyboard=%B6%AF%C2%FE&submit='

def search(text):
    secondDir = (firstDir + '\\' + text).replace('\\', '/')  # 分类目录
    text_gbk = text.encode('gbk')
    text_str = str(text_gbk).replace('\\', 'x')
    text_str_split = text_str.split(r'xx')
    text_str_split[4] = text_str_split[4].split("'")[0]
    text_str_split = text_str_split[1:]
    code_arg = '%' + '%'.join(text_str_split).upper() + '&submit='
    print(code_arg)
    #对首页图片就行处理

    select = 'div#main div.list ul li a'
    url = index+'/e/sch/index.php?keyboard='+code_arg
    start_page_imgs = screen(url,select)
    handleImgs(start_page_imgs, secondDir)  # 对每页中的图片就行处理


    select = 'div.page a'
    page_links = screen(url,select)[:-2]
    print(page_links)
    if len(page_links) != 0:
        for link in page_links:
            href = link.get('href').replace(text,code_arg)
            url = index + href
            select = 'div#main div.list ul li a'
            imgUrls = screen(url, select)
            handleImgs(imgUrls, secondDir)  # 对每页中的图片就行处理
    else:print('没有图片')

    print('it is over~')


search('动漫')#下载什么输入什么

在最后的代码文本处填入你想要下载的图片类型，函数作用是调用网站的搜索接口，就行图片链接的获取。整体结构非常简单，通过BeautifulSoup来解析链接，requests来发送请求。

有些时候你的cookie会被暂时禁用，所以随机跟换一下头文件。

import random

user_agent = [
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
    "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
    "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
    "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
    "UCWEB7.0.2.37/28/999",
    "NOKIA5700/ UCWEB7.0.2.37/28/999",
    "Openwave/ UCWEB7.0.2.37/28/999",
    "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
    # iPhone 6
	"Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
    # 新版移动ua
    "Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"
]

# 随机获取一个请求头
def get_headers():
    return {'User-Agent': random.choice(user_agent)}