Weibo_Crawler/get_weibo_content/get_time.py

from lxml import etree
import time
from get_weibo_content.process_data import remove_html_tags, html_unicode_2_chinese, process_str


def get_time(html, flag, date_begin):
    selector = etree.HTML(html)
    weibo_time = selector.xpath('//div[@class="content"]/p[2]/a[1]')
    weibo_time_str = []
    count = 0
    count_s = 0
    for i in weibo_time:
        if count in flag:
            temp = remove_html_tags(etree.tostring(selector.xpath('//div[@class="content"]/p[3]/a[1]')[count_s]))
            count_s += 1
        else:
            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
        weibo_time_str.append(temp)
        count += 1
    return weibo_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