下载图片的核心代码如下:
res = requests.get(url=img_url, headers=headers)
if 200 == res.status_code:
with open(file_path, 'wb') as file:
file.write(res.content)
使用requests库,直接对图片的url进行请求,如果返回状态码为200(ok)的话,那么get方法返回的content二进制串即为图片的真实内容,我们只需将其写入文件即可。
下面的示例代码中加入了路径的处理。
import requests
import random
import os
class PicDownloader():
def __init__(self):
self.count = 0 # 用于文件编号
self.file_name = 'img' # 默认文件名
self.working_dir = '.' # 默认工作目录
def download_img(self, img_url, dir='.'):
'''
下载url指定的图片到本地dir目录
'''
self.count += 1
self.file_name = self.file_name + '_' + str(self.count) + '.jpg'
# 如果指定的下载目录不存在,则尝试创建
if os.path.isdir(dir):
self.working_dir = dir
else:
try:
os.makedirs(dir)
self.working_dir = dir
except OSError as e:
print(f'create dir: {dir} failed')
# 生成完整的路径名
file_path = os.path.join(self.working_dir, self.file_name)
print(f'开始下载文件:{file_path}')
headers = self.get_headers()
try:
res = requests.get(url=img_url, headers=headers)
if 200 == res.status_code:
with open(file_path, 'wb') as file:
file.write(res.content)
except Exception as e:
print(f'下载文件失败: {file_path}')
print(repr(e))
print('文件下载成功')
# 供爬虫使用的,此例中并不需要这么多,随便取一种就行了
def get_headers(self):
user_agent_list = [
"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 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"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 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
"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 (Macintosh; Intel Mac OS X 10_8_0) 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 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"]
userAgent = random.choice(user_agent_list)
headers = {'User-Agent': userAgent}
return headers
if __name__== '__main__':
downloader = PicDownloader()
downloader.download_img('https://images.weserv.nl/?url=https%3A%2F%2F23img.com%2Fi%2F2022%2F08%2F17%2Fqykvvx.jpg', 'd:/test')
效果如下: