python 爬虫练习

最新推荐文章于 2022-02-26 14:46:51 发布

原创

最新推荐文章于 2022-02-26 14:46:51 发布 · 1.1k 阅读

7 ·

CC 4.0 BY-SA版权

http://www.cbrc.gov.cn/chinese/jrjg/index.html
爬取所有银行的银行名称和官网地址(如果没有官网就忽略)，并写入数据库；

import re
from urllib.request import urlopen
from urllib import request

import pymysql


def getbank():
    url = 'http://www.cbrc.gov.cn/chinese/jrjg/index.html'
    user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0'
    req = request.Request(url, headers={'User-Agent':user_agent})
    content = urlopen(req).read().decode('utf-8')
    print("正在爬取地址")
    pattern = r'<a href="(?P<bankaddress>.+)" target="_blank" style="color:#08619D">\s*(?P<bankname>[\u4e00-\u9fa5]+)\s*</a>'
    findbankadd = re.findall(pattern,content)
    print(findbankadd)
    conn = pymysql.connect(user='root',
                           password='971203', charset='utf8', autocommit=True)
    cur = conn.cursor()
    conn.select_db('bank')
    create_sql = 'create table