Python爬取某网站图片的简单实现

1.代码

代码如下（示例）：

import random
import requests
import re
import time
import os
import threading
from lxml import etree
# 设置最大线程锁
thread_lock = threading.BoundedSemaphore(value=200)

# 在桌面创建了一个文件夹，用于存放图片
Address1 = r'C:\Users\***\Desktop\新建文件夹 (2)\{}'

# headers可以在浏览器，检查，Network中查找，不加headers极容易被目标网站视为攻击
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
}

# 爬取的目标网站
url_main='https://*******/index.php/art/type/id/30.html'

def jiexi_main(url):
    '''
    解析目标网站的列表地址
    :param url:
    :return: 传回目标网站的列表子地址
    '''
    response1 = requests.get(url, headers=headers)
    html1 = response1.text
    res_xpath = etree.HTML(response1.text)
    urls=res_xpath.xpath('/html/body/div[2]/div[3]/div/div/ul/li/a/@href')
    print(urls)# 输出检查是否为子地址全址，在main1中是否需要添加部分地址
    return urls


def jiexi_url(url):
    '''解析单个网页'''
    response = requests.get(url, headers=headers)
    html = response.text
    urls = re.findall('<img src="(.*?)"/>', html)  # 正则截取图片地址
    print(urls) # 输出目标图片地址，判断是否截取成功
    response.close()
    return urls



def download_pics(url,n,path):
    '''保存图片'''
    time.sleep(1)
    # 图片名称
    file_name = url.split('/')[-1]
    response = requests.get(url, headers=headers)
    with open(path+"\{}.jpg".format(file_name), 'wb') as f:
        f.write(response.content)
        print('下载完成第{}张图片'.format(n))
        # 下载完，解锁
        thread_lock.release()


def main_1():
    '''
    可下载列表
    :return:
    '''

    start = time.time()
    # 此处做了一个多个列表页目标爬取的尝试，没有成功
    # for index in range(4,10,1):
    #     print(index)
    #     url_main1 = url_main.format(index)
    #     url_main_pic = jiexi_main(url_main1)
    url_main_pic=jiexi_main(url_main)
    file_name = '8'  # 下载图片所要存放的子文件夹名
    m = './' + file_name
    if not os.path.exists(Address1.format(m)):
        os.mkdir(Address1.format(m))
    path = Address1.format(m)
    n = 0
    m = 0
    for url_py in url_main_pic:
        m += 1
        time.sleep(0.5)
        pic_urls = jiexi_url('https://dj66.pw' + url_py)
        for url in pic_urls:
            n += 1
            print('正在下载_{}'.format(n))
            # print('正在下载第{}张图片'.format(n))
            # 上锁
            thread_lock.acquire()
            t = threading.Thread(target=download_pics, args=(url, n, path))
            t.start()


    end = time.time() # 做了一个程序运行的计时 
    print('Running time: %s Seconds' % (end - start))  # 输出程序运行时间


def main_2():
    '''
    可下载单个图片页地址
    :return:
    '''
    url_py='https://******/index.php/art/detail/id/35231.html' # 可以修改该地址进行不同页面图片的下载
    start = time.time()
    n = 0
    file_name='5'
    m = './'+file_name
    pic_urls = jiexi_url(url_py)
    if not os.path.exists(Address1.format(m)):
        os.mkdir(Address1.format(m))
    path=Address1.format(m)
    for url in pic_urls:
        n += 1
        # print('正在下载第{}张图片'.format(n))
        # 上锁
        thread_lock.acquire()
        t = threading.Thread(target=download_pics, args=(url,n,path))
        t.start()
    end = time.time()
    print('Running time: %s Seconds' % (end - start))  # 输出程序运行时间


# 分别可以调用两个主程序
if __name__=='__main__':
    main_1()
#if __name__=='__main__':
#    main_1()

2.读入数据

代码如下（示例）：

C:\Users\lee\PycharmProjects\python_Pachong\venv\Scripts\python.exe C:/Users/lee/PycharmProjects/python_Pachong/tupian.py
['/index.php/art/detail/id/32605.html', '/index.php/art/detail/id/32604.html', '/index.php/art/detail/id/32603.html', '/index.php/art/detail/id/32602.html', '/index.php/art/detail/id/32601.html', '/index.php/art/detail/id/32551.html', '/index.php/art/detail/id/32550.html', '/index.php/art/detail/id/32549.html', '/index.php/art/detail/id/32548.html', '/index.php/art/detail/id/32547.html', '/index.php/art/detail/id/32504.html', '/index.php/art/detail/id/32503.html', '/index.php/art/detail/id/32502.html', '/index.php/art/detail/id/32501.html', '/index.php/art/detail/id/32500.html', '/index.php/art/detail/id/32454.html', '/index.php/art/detail/id/32453.html', '/index.php/art/detail/id/32452.html', '/index.php/art/detail/id/32451.html', '/index.php/art/detail/id/32450.html', '/index.php/art/detail/id/32400.html', '/index.php/art/detail/id/32399.html', '/index.php/art/detail/id/32398.html', '/index.php/art/detail/id/32397.html', '/index.php/art/detail/id/32396.html', '/index.php/art/detail/id/32352.html', '/index.php/art/detail/id/32351.html', '/index.php/art/detail/id/32350.html', '/index.php/art/detail/id/32349.html', '/index.php/art/detail/id/32348.html']
['https://mei.lbpicmt.com/upload/art/img/lctk/85f99c8dae715a22578e1f95873a930d.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/6b0adeba5f567b47af2174d6cb9a6a52.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/857742df813b50596189eb229c600208.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/f99ebf01b38b74397d31edec5f5a3f03.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/b21b4a95ad6fac05bb1693ac0b7b70e8.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/f61e8cebf99028c552673680f1b5b5c8.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/a355c9fc2ac0d3a6f2cb126002591d2b.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/a2886729e6792e73382a82f8ffb8be89.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/b7bd5589f078d9c2eed5ec65687ef88e.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/2506d711d0949e5f73aa44e6995840ec.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/6362cd69504fde74961f0f79666ddd21.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/74c47d60954cf559cf42d6707daf23d0.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/0379cfef889808eacd04da4543f656b5.jpg']
正在下载_1
正在下载_2
正在下载_3
正在下载_4
正在下载_5
正在下载_6
正在下载_7
正在下载_8
正在下载_9
正在下载_10
正在下载_11
正在下载_12
正在下载_13
['https://mei.lbpicmt.com/upload/art/img/lctk/98db56003c1d6392e94569102667cdf1.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/33b57eaaf30a1c99042ad639af1dd591.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/fc827e5d9f91bc293336c55b8b7fa8b6.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/a5ff04d37b2811814408b76339270ed1.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/6e79ac0cb5364c047ea77cbbfd946bea.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/c6b8a0e80b7c7d80ab435ff1cc5ed683.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/1275f9f465d24a4773253013b5348fd4.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/f1dcf4d39e4dca88793d1e5bfff862b6.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/bcba83d63cac2f4ab2c041693be8fee8.jpg', 'https://mei.lbpicmt.com/upload/art/img/lctk/0f50a5e66b76ed76abd0bb50019bf94e.jpg']
正在下载_14
正在下载_15
正在下载_16
正在下载_17
正在下载_18
正在下载_19
正在下载_20
正在下载_21
正在下载_22
正在下载_23
下载完成第7张图片
下载完成第8张图片

---

总结

可以爬取目标网站的图片，但是还有很多问题

运行过程中会报以下错误

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\adapters.py", line 439, in send
    resp = conn.urlopen(
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\connectionpool.py", line 726, in urlopen
    retries = retries.increment(
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\util\retry.py", line 403, in increment
    raise six.reraise(type(error), error, _stacktrace)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\packages\six.py", line 734, in reraise
    raise value.with_traceback(tb)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\connectionpool.py", line 670, in urlopen
    httplib_response = self._make_request(
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\connectionpool.py", line 381, in _make_request
    self._validate_conn(conn)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\connectionpool.py", line 978, in _validate_conn
    conn.connect()
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\connection.py", line 362, in connect
    self.sock = ssl_wrap_socket(
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\urllib3\util\ssl_.py", line 384, in ssl_wrap_socket
    return context.wrap_socket(sock, server_hostname=server_hostname)
  File "C:\Users\lee\AppData\Local\Programs\Python\Python38-32\lib\ssl.py", line 500, in wrap_socket
    return self.sslsocket_class._create(
  File "C:\Users\lee\AppData\Local\Programs\Python\Python38-32\lib\ssl.py", line 1040, in _create
    self.do_handshake()
  File "C:\Users\lee\AppData\Local\Programs\Python\Python38-32\lib\ssl.py", line 1309, in do_handshake
    self._sslobj.do_handshake()
urllib3.exceptions.ProtocolError: ('Connection aborted.', ConnectionResetError(10054, '远程主机强迫关闭了一个现有的连接。', None, 10054, None))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:/Users/lee/PycharmProjects/python_Pachong/tupian.py", line 125, in <module>
    main_1()
  File "C:/Users/lee/PycharmProjects/python_Pachong/tupian.py", line 83, in main_1
    pic_urls = jiexi_url('https://dj66.pw' + url_py)
  File "C:/Users/lee/PycharmProjects/python_Pachong/tupian.py", line 36, in jiexi_url
    response = requests.get(url, headers=headers)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\api.py", line 76, in get
    return request('get', url, params=params, **kwargs)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\api.py", line 61, in request
    return session.request(method=method, url=url, **kwargs)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\sessions.py", line 530, in request
    resp = self.send(prep, **send_kwargs)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\sessions.py", line 643, in send
    r = adapter.send(request, **kwargs)
  File "C:\Users\lee\PycharmProjects\python_Pachong\venv\lib\site-packages\requests\adapters.py", line 498, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(10054, '远程主机强迫关闭了一个现有的连接。', None, 10054, None))