Last active
May 14, 2017 12:44
-
-
Save joyc/8d7819f68d07aaf18ee573f72b1baa03 to your computer and use it in GitHub Desktop.
download ranking photos from wear.jp
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! python3 | |
# -*- coding:utf-8 -*- | |
# @Time : 2017/05/13 19:06 | |
# @Author : Hython.com | |
# @File : wear.py - Download the new ranking image from wear.jp | |
# @IDE : PyCharm | |
import requests, os, bs4, sys | |
# 要下载图片的页面地址 | |
keyword = ''.join(sys.argv[1:]) | |
if keyword == '': | |
rankPage = 'http://wear.jp/ranking/' | |
else: | |
rankPage = 'http://wear.jp/' + keyword + '-ranking/' | |
# 保存到指定目录 | |
os.chdir('C:\\Users\\rockb_000\\Desktop\\Wear-Photo') | |
print('已保存到目录-→ ' + os.getcwd()) | |
os.makedirs('wear-' + keyword + '-ranking', exist_ok=True) | |
while not rankPage.endswith('#'): | |
print('下载图片中。。。') | |
# 下载整个页面 | |
res = requests.get(rankPage) | |
try: | |
res.raise_for_status() | |
except Exception as exc: | |
print('There was a problem: %s' % (exc)) | |
soup = bs4.BeautifulSoup(res.text, "html.parser") | |
# 查找图片地址并保存 | |
imgElem = soup.select('div.image > a > p > img') | |
if imgElem == []: | |
print('什么也没找到。。。') | |
else: | |
for i in range(len(imgElem)): | |
url = imgElem[i].get('src') | |
res = requests.get(url) | |
res.raise_for_status() | |
imgFile = open(os.path.join('wear-' + keyword + '-ranking', os.path.basename(url)), 'wb') | |
for chunk in res.iter_content(100000): | |
imgFile.write(chunk) | |
imgFile.close() | |
rankPage = '#' | |
print('下载结束!') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment