源码
import requests
import json
def download(src, id):
dir = './' + str(id) + '.jpg'
try:
pic = requests.get(src, timeout=10)
except requests.exceptions.ConnectionError:
# print 'error, %d 当前图片无法下载', %id
print('图片无法下载')
fp = open(dir, 'wb')
fp.write(pic.content)
fp.close()
def loop_request(total, text):
for i in range(0, total, 20):
url = 'https://www.douban.com/j/search_photo?q=' + text + '&limit=20&start=' + str(i)
html = requests.get(url).text # 得到返回结果
response = json.loads(html, encoding='utf-8') # 将JSON格式转换成Python对象
for image in response['images']:
print('downloading ' + image['src'])
# 查看当前下载的图片网址
download(image['src'], image['id']) # 下载一张图片
def get_count(text):
url = 'https://www.douban.com/j/search_photo?q=' + text + '&limit=20&start=1'
html = json.loads(requests.get(url).text, encoding='utf-8')
print(html)
print(html['total'])
loop_request(html['total'], text)
get_count('周杰伦')
简要说明
- 其中包含三个函数
- get_count用于获取该关键字对应图片的数量
- loop_request根据图片总数量,20个一组获取图片
- download下载图片并根据id保存至本地
环境介绍
- python版本 3.0+
- 开发工具 PyCharm
END