本文是本人最近学习Python爬虫所做的小练习。
如有侵权,请联系删除
。
页面获取url
代码
python
import requests
import os
import re
# 创建文件夹
path = os.getcwd() + '/images'
if not os.path.exists(path):
os.mkdir(path)
# 获取全部数据
def get_data():
# 地址
url = "https://movie.douban.com/j/search_subjects"
# 传参
params = {
'type': 'movie',
'tag': '豆瓣高分',
'page_limit': 50,
'page_start': 0
}
# 请求头
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'
}
# 发送请求
response = requests.get(url, params=params, headers=headers)
# json数据格式
items = response.json()
# 循环遍历
for data in items['subjects']:
# 标题
title = data.get('title')
# 封面
cover = data.get('cover')
# 下载图片到images文件夹,文件名:title
if title != '' and cover != '':
download_image(title, cover)
# 下载图片
def download_image(title, cover):
# 请求头
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'
}
res = requests.get(cover, headers=headers)
# 判断标题是否含有\/:*?"<>|,文件命名不能含有这些,如果有,则用下划线_取代
new_title = validateTitle(title)
with open(path + '/' + new_title + '.jpg', mode='wb') as f:
# 图片内容写入文件
f.write(res.content)
print(f"正在下载图片,图片名:{title}.jpg")
# 去除文件中的非法字符(正则表达式)
def validateTitle(title):
pattern = r"[\\\/\:\*\?\"\<\>\|]"
new_title = re.sub(pattern, '_', title)
return new_title
if __name__ == '__main__':
get_data()