阅读 1319

总说手机没有“好壁纸”,Python一次性抓取500张“美女”图片,够不够用!

作者:JackTian
来源:杰哥的IT之旅(ID:Jake_Internet)
转载请联系授权(微信ID:Hc220088)

原文链接:总说手机没有“好壁纸”,Python一次性抓取500张“美女”图片,够不够用!

图片

1.爬取一页的图片

正则匹配提取图片数据

网页源代码部分截图如下:

图片

图片

重新设置 GBK 编码解决了乱码问题

图片

代码实现:

import requests
import re

# 设置保存路径
path = r'D:\test\picture_1\ '
# 目标url
url = "http://pic.netbian.com/4kmeinv/index.html"
# 伪装请求头  防止被反爬
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Referer": "http://pic.netbian.com/4kmeinv/index.html"
}

# 发送请求  获取响应
response = requests.get(url, headers=headers)
# 打印网页源代码来看  乱码   重新设置编码解决编码问题
# 内容正常显示  便于之后提取数据
response.encoding = 'GBK'

# 正则匹配提取想要的数据  得到图片链接和名称
img_info = re.findall('img src="(.*?)" alt="(.*?)" /', response.text)

for src, name in img_info:
    img_url = 'http://pic.netbian.com' + src   # 加上 'http://pic.netbian.com'才是真正的图片url
    img_content = requests.get(img_url, headers=headers).content
    img_name = name + '.jpg'
    with open(path + img_name, 'wb') as f:     # 图片保存到本地
        print(f"正在为您下载图片:{img_name}")
        f.write(img_content)
复制代码

Xpath定位提取图片数据

图片

图片

代码实现:

import requests
from lxml import etree

# 设置保存路径
path = r'D:\test\picture_1\ '
# 目标url
url = "http://pic.netbian.com/4kmeinv/index.html"
# 伪装请求头  防止被反爬
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Referer": "http://pic.netbian.com/4kmeinv/index.html"
}

# 发送请求  获取响应
response = requests.get(url, headers=headers)
# 打印网页源代码来看  乱码   重新设置编码解决编码问题
# 内容正常显示  便于之后提取数据
response.encoding = 'GBK'
html = etree.HTML(response.text)
# xpath定位提取想要的数据  得到图片链接和名称
img_src = html.xpath('//ul[@class="clearfix"]/li/a/img/@src')
# 列表推导式   得到真正的图片url
img_src = ['http://pic.netbian.com' + x for x in img_src]
img_alt = html.xpath('//ul[@class="clearfix"]/li/a/img/@alt')

for src, name in zip(img_src, img_alt):
    img_content = requests.get(src, headers=headers).content
    img_name = name + '.jpg'
    with open(path + img_name, 'wb') as f:   # 图片保存到本地
        print(f"正在为您下载图片:{img_name}")
        f.write(img_content)
复制代码

2.翻页爬取,实现批量下载

图片

单线程版

import requests
from lxml import etree
import datetime
import time

# 设置保存路径
path = r'D:\test\picture_1\ '
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Referer": "http://pic.netbian.com/4kmeinv/index.html"
}
start = datetime.datetime.now()

def get_img(urls):
    for url in urls:
        # 发送请求  获取响应
        response = requests.get(url, headers=headers)
        # 打印网页源代码来看  乱码   重新设置编码解决编码问题
        # 内容正常显示  便于之后提取数据
        response.encoding = 'GBK'
        html = etree.HTML(response.text)
        # xpath定位提取想要的数据  得到图片链接和名称
        img_src = html.xpath('//ul[@class="clearfix"]/li/a/img/@src')
        # 列表推导式   得到真正的图片url
        img_src = ['http://pic.netbian.com' + x for x in img_src]
        img_alt = html.xpath('//ul[@class="clearfix"]/li/a/img/@alt')
        for src, name in zip(img_src, img_alt):
            img_content = requests.get(src, headers=headers).content
            img_name = name + '.jpg'
            with open(path + img_name, 'wb') as f:  # 图片保存到本地
                # print(f"正在为您下载图片:{img_name}")
                f.write(img_content)
        time.sleep(1)

def main():
    # 要请求的url列表
    url_list = ['http://pic.netbian.com/4kmeinv/index.html'] + [f'http://pic.netbian.com/4kmeinv/index_{i}.html' for i in range(2, 11)]
    get_img(url_list)
    delta = (datetime.datetime.now() - start).total_seconds()
    print(f"抓取10页图片用时:{delta}s")

if __name__ == '__main__':
    main()
复制代码

程序运行成功,抓取了10页的图片,共210张,用时63.682837s。

图片

多线程版

import requests
from lxml import etree
import datetime
import time
import random
from concurrent.futures import ThreadPoolExecutor

# 设置保存路径
path = r'D:\test\picture_1\ '
user_agent = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    ]
start = datetime.datetime.now()

def get_img(url):
    headers = {
        "User-Agent": random.choice(user_agent),
        "Referer": "http://pic.netbian.com/4kmeinv/index.html"
    }
    # 发送请求  获取响应
    response = requests.get(url, headers=headers)
    # 打印网页源代码来看  乱码   重新设置编码解决编码问题
    # 内容正常显示  便于之后提取数据
    response.encoding = 'GBK'
    html = etree.HTML(response.text)
    # xpath定位提取想要的数据  得到图片链接和名称
    img_src = html.xpath('//ul[@class="clearfix"]/li/a/img/@src')
    # 列表推导式   得到真正的图片url
    img_src = ['http://pic.netbian.com' + x for x in img_src]
    img_alt = html.xpath('//ul[@class="clearfix"]/li/a/img/@alt')
    for src, name in zip(img_src, img_alt):
        img_content = requests.get(src, headers=headers).content
        img_name = name + '.jpg'
        with open(path + img_name, 'wb') as f:  # 图片保存到本地
            # print(f"正在为您下载图片:{img_name}")
            f.write(img_content)
    time.sleep(random.randint(1, 2))

def main():
    # 要请求的url列表
    url_list = ['http://pic.netbian.com/4kmeinv/index.html'] + [f'http://pic.netbian.com/4kmeinv/index_{i}.html' for i in range(2, 51)]
    with ThreadPoolExecutor(max_workers=6) as executor:
        executor.map(get_img, url_list)
    delta = (datetime.datetime.now() - start).total_seconds()
    print(f"爬取50页图片用时:{delta}s")

if __name__ == '__main__':
    main()
复制代码

程序运行成功,抓取了50页图片,共1047张,用时56.71979s。开多线程大大提高的爬取数据的效率。

图片

最终成果如下:

图片

原创不易,码字不易,如果你觉得这篇文章对你有点用的话,欢迎点赞、留言、转发分享让更多的掘友看到,因为这将是我持续输出更多优质文章的最强动力,谢谢大家!

文章分类
后端