(page_bytes, charsets=('utf-8',))
| 16 | |
| 17 | # 通过指定的字符集对页面进行解码(不是每个网站都将字符集设置为utf-8) |
| 18 | def decode_page(page_bytes, charsets=('utf-8',)): |
| 19 | page_html = None |
| 20 | for charset in charsets: |
| 21 | try: |
| 22 | page_html = page_bytes.decode(charset) |
| 23 | break |
| 24 | except UnicodeDecodeError: |
| 25 | pass |
| 26 | # logging.error('[Decode]', err) |
| 27 | return page_html |
| 28 | |
| 29 | |
| 30 | # 获取页面的HTML代码(通过递归实现指定次数的重试操作) |