A record | 爬取论文名

import requests
import urllib.request
from bs4 import BeautifulSoup
import json


def bs_parse_names(html):
    global tname_list
    tname_list = []
    soup = BeautifulSoup(html, "lxml")
    # 查找所有class属性为list-group-item的div标签
    div_list = soup.find_all('div', class_='list-group-item')# 通过find定位标签
    # 获取每个div中的b中的span（第一个），并获取其文本
    for each in div_list:
        tname = each.b.text.strip()
        tname_list.append(tname)
    return tname_list


def get_tname():
    response=urllib.request.urlopen('http://www.ieee-security.org/TC/SP2019/program-papers.html')#要爬取的网页链接
    return bs_parse_names(response.read().decode('utf-8'))


def write_to_file(content):#写入文件
    with open('19ssp.txt','a',encoding='utf-8') as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content,ensure_ascii=False)+'\n')


tname = get_tname()
print(tname)
for each in tname_list:
    write_to_file(each)