python 爬取36K新闻

代码如下：

from urllib import request
url = 'http://36kr.com/api/info-flow/newsflash_columns/newsflashes?b_id=65698&per_page=20&_=1498272599297'
req = request.Request(url)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36')
resp = request.urlopen(req)
print('Status:', resp.status, resp.reason)
if 200 == resp.status:
    data = resp.read().decode('utf-8')
else:
    print('Status Error!\n')
    exit(0)
#使用with打开文件会自动帮你关闭文件
with open('E:\\data.txt', 'w') as f:
    f.write(data)
import json
json_data = json.loads(data)
with open('E:\\json_data.txt', 'w', encoding='utf-8') as f:
    json.dump(json_data, f, indent=4, ensure_ascii=False)
for news in json_data['data']['items']:
    print(news['title']+'\n'+news['updated_at'] + '\n' + news['description'] + '\n\n')
print('\nDone!\n')

爬取效果图：