获取url地址页面内容
(url)
| 14 | |
| 15 | |
| 16 | def download_page(url): |
| 17 | """获取url地址页面内容""" |
| 18 | headers = { |
| 19 | 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36' |
| 20 | } |
| 21 | data = requests.get(url, headers=headers).content |
| 22 | return data |
| 23 | |
| 24 | |
| 25 | def get_li(doc): |