下载豆瓣 王祖贤的海报
- 使用request请求URL得到返回结果
- 将JSON格式转换成Python对象
- 在response 里查看当前下载的图片网址
- 下载保存图片
import requests
import json
query = '王祖贤'
''' 下载图片 '''
def download(src, id):
dir = './' + str(id) + '.jpg'
try:
pic = requests.get(src, timeout=10)
except requests.exceptions.ConnectionError:
print('图片无法下载')
fp = open(dir, 'wb')
fp.write(pic.content)
fp.close()
''' for循环 请求全部的url '''
for i in range(0, 22471, 20):
url = 'https://www.douban.com/j/search_photo?q='+query+'&limit=20&start='+str(i)
html = requests.get(url).text
response = json.loads(html,encoding='utf-8')
for image in response['images']:
print(image['src'])
download(image['src'], image['id'])
下载豆瓣爱情的电影封面
- 构造url,翻页变换参数为start=, tag=电影, gender=爱情, 改变start=后面的数字,可以爬取不同的页
- 使用request请求URL得到返回结果
- 将JSON格式转换成Python对象
- 在response 里查看当前下载的图片网址
- 下载保存图片
import requests
import json
def download(url, title):
dir = './' + title + '.jpg'
try:
pic = requests.get(url)
fp = open(dir, 'wb')
fp.write(pic.content)
fp.close()
print(title)
except requests.exceptions.ConnectionError:
print('图片无法下载')
for num in range(0, 1000, 20):
url = 'https://movie.douban.com/j/new_search_subjects?sort=U&range=0,10&tags=%E7%94%B5%E5%BD%B1&start='\
+ str(num)+'&genres=%E7%88%B1%E6%83%85'
print(url)
html = requests.get(url).text
res = json.loads(html, encoding='utf-8')
for result in res['data']:
cover = result['cover']
title = result['title']
download(cover, title)