| 123456789101112131415161718192021222324252627282930 |
- from lxml import etree
- import time
- from .ProcessTool import remove_html_tags, html_unicode_2_chinese, process_str
- def get_time(html, date_begin):
- selector = etree.HTML(html)
- wei_bo_time = selector.xpath('//div[@class="content"]/p[1]/a[1]')
- wei_bo_time_str = []
- for i in wei_bo_time:
- temp = remove_html_tags(etree.tostring(i))
- temp = html_unicode_2_chinese(temp)
- temp = process_str(temp)
- temp = reprocess_str(temp)
- if '今天' in temp:
- temp = temp.replace('今天', ' ')
- temp = time.strftime("%Y-%m-%d", time.localtime()) + temp
- else:
- temp = date_begin[0:4] + '-' + temp
- wei_bo_time_str.append(temp)
- return wei_bo_time_str
- def reprocess_str(unprocessed_str):
- temp = unprocessed_str.replace(' ', '')
- temp = temp.replace('来自', '')
- temp = temp.replace('\xa0', '')
- temp = temp.replace('月', '-')
- temp = temp.replace('日', '-')
- return temp
|
