高校、专利信息

LEMONwhale

已于 2022-03-08 21:17:37 修改

阅读量1k

点赞数

文章标签：爬虫 python

于 2022-03-08 21:13:56 首次发布

本文链接：https://blog.csdn.net/weixin_44812575/article/details/123363222

版权

# -*- coding:utf-8  -*-

from bs4 import BeautifulSoup
import urllib.request
import re
import xlwt
from urllib.parse import quote
import json

def main():
    baseurl = 'https://baike.baidu.com/item/'
    print("0")
    #爬取网页
    datalist = getdata(baseurl)


def school_list(filename):
    school = []
    fr = open(filename, 'r', encoding='utf-8')
    lines = fr.readlines()
    for line in lines:
        school.append(line.strip('\n'))
    fr.close()
    return school


def getdata(baseurl):
    print("1")
    school = school_list('school.txt')
    datalist=[]
    for index in school:
        url = baseurl + urllib.parse.quote(index)
        html=askurl(url)
        #逐一解析
        soup = BeautifulSoup(html,"html.parser")
        name_data = []
        value_data = []
        name_node = soup.find_all('dt', class_='basicInfo-item name')

        for i in range(len(name_node)):
            name_data.append(name_node[i].get_text().replace('\xa0', ''))
            # name_data.append(name_node[i].get_text())
            #
        value_node = soup.find_all('dd', class_='basicInfo-item value')
        for i in range(len(value_node)):
            value_data.append(value_node[i].get_text().replace('\n', ''))
            # print(type(value_node[i].get_text().replace('\n', '')))
            # print(value_node[i].get_text().replace('\n', ''))
            # print(value_data)
            # print(type(value_data))
        result = {'中文名': '无信息', '英文名':