Python3直接爬取图片URL并保存示例

def getUrls(path):
  urls = []
  with open(path,'r') as f:
    for line in f:
      urls.append(line.strip('\n'))
  return(urls)

def requestImg(url, name, num_retries=3):
  img_src = url
  # print(img_src)
  header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64)     AppleWebKit/537.36 (KHTML, like Gecko)       Chrome/35.0.1916.114 Safari/537.36',
    'Cookie': 'AspxAutoDetectCookieSupport=1'
  }
  # Request类可以使用给定的header访问URL
  req = urllib.request.Request(url=img_src, headers=header) 
  try:
    response = urllib.request.urlopen(req) # 得到访问的网址
    filename = name + '.jpg'
    with open(filename, "wb") as f:
      content = response.read() # 获得图片
      f.write(content) # 保存图片
      response.close()
  except HTTPError as e: # HTTP响应异常处理
    print(e.reason)
  except URLError as e: # 一定要放到HTTPError之后，因为它包含了前者
    print(e.reason)
  except IncompleteRead or RemoteDisconnected as e: 
    if num_retries == 0: # 重连机制
      return
    else:
      requestImg(url, name, num_retries-1)

def clock(func): # 修饰器函数，对函数计时
  def clocked(*args):
    t0 = timeit.default_timer()
    result = func(*args)
    elapsed = timeit.default_timer() - t0
    name = func.__name__
    arg_str = ', '.join(repr(arg) for arg in args)
    print('[%0.8fs] %s(%s)' % (elapsed, name, arg_str))
    # print('%s(%s) -> %r [%0.8fs]' % (name, arg_str, result, elapsed))
    return result
  return clocked

@clock

from urllib.error import HTTPError, URLError
from http.client import IncompleteRead, RemoteDisconnected
import timeit, time
import urllib.request
import socket
 
 
# timeout = 20
# socket.setdefaulttimeout(timeout) # 等待，防止被简单地反爬
 
 
def getUrls(path):
  urls = []
  with open(path,'r') as f:
    for line in f:
      urls.append(line.strip('\n'))
  return(urls)
 
 
def clock(func): # 修饰器函数，对函数计时
  def clocked(*args):
    t0 = timeit.default_timer()
    result = func(*args)
    elapsed = timeit.default_timer() - t0
    name = func.__name__
    arg_str = ', '.join(repr(arg) for arg in args)
    print('[%0.8fs] %s(%s)' % (elapsed, name, arg_str))
    # print('%s(%s) -> %r [%0.8fs]' % (name, arg_str, result, elapsed))
    return result
  return clocked
 
 
@clock
def requestImg(url, name, num_retries=3):
  img_src = url
  # print(img_src)
  header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64)     AppleWebKit/537.36 (KHTML, like Gecko)       Chrome/35.0.1916.114 Safari/537.36',
    'Cookie': 'AspxAutoDetectCookieSupport=1'
  }
  req = urllib.request.Request(url=img_src, headers=header)
  try:
    response = urllib.request.urlopen(req)
    filename = name + '.jpg'
    with open(filename, "wb") as f:
      content = response.read()
      f.write(content)
      response.close()
  except HTTPError as e:
    print(e.reason)
  except URLError as e:
    print(e.reason)
  except IncompleteRead or RemoteDisconnected as e:
    if num_retries == 0:
      return
    else:
      requestImg(url, name, num_retries-1)
 
 
 
if __name__ =='__main__':
  urls = getUrls('./'URLS.txt') # 换成你的URL文件路径
  nLines = len(urls)
  print(nLines)
  for index, value in enumerate(urls):
      requestImg(value, './'+str(index).zfill(6)) # zfill用来格式化数字：000001