爬虫

import urllib.request
from bs4 import BeautifulSoup, SoupStrainer
import re

lis_str = []


def for_list(list_x):
    for x in list_x:
        if len(x) > 1:
            for_list(x)
        else:
            # 过滤所有标签
            pattern = re.compile("<(.*?)>")
            lis_str.append(re.sub(pattern, "", str(x)))


if __name__ == '__main__':
    url=''.strip()
    reponse = urllib.request.urlopen(url)
    only_a_tags = SoupStrainer('div', attrs={"class": "vF_detail_content_container"})
    p_x_list = BeautifulSoup(reponse.read().decode('utf-8'), 'html.parser', parse_only=only_a_tags)
    for_list(p_x_list)
    count = len(lis_str)
    filter_lis = ['采购', '联系', '中标', '电话', '传真', '成交']
    for i in range(count):
        if bool(re.compile(u'[\u4e00-\u9fa5]').search(lis_str[i])) or bool(re.search(r'\d', lis_str[i])):
            if '采购' in lis_str[i] or '联系' in lis_str[i] or '中标' in lis_str[i] or '电话' in lis_str[i] or '传真' in lis_str[
                i] or '成交' in lis_str[i]:
                datas.append(lis_str[i])