Python3爬虫全国地址信息

Python  /  管理员 发布于 7年前   188

PHP方式写的一团糟所以就用python3重写了一遍，所以因为第二次写了，思路也更清晰了些。

提醒：可能会有502的错误，所以做了异常以及数据库事务处理，暂时没有想到更好的优化方法，所以就先这样吧。待更懂python再进一步优化哈

欢迎留言赐教~

#!C:\Users\12550\AppData\Local\Programs\Python\Python37\python.exe# -*- coding: utf-8 -*-from urllib.request import urlopenfrom bs4 import BeautifulSoupimport pymysqlimport urllib.requestimport refrom urllib.error import URLError, HTTPErrorconn = pymysql.connect(host='127.0.0.1', user='root', passwd='root', db='test', charset='utf8')db = conn.cursor()curr_url = ''# 请求网页def get_html(url):  global curr_url  user_agent = 'Mozilla/6.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.6796.99 Safari/537.36'  response = urllib.request.Request(url)  response.add_header('User-Agent', user_agent)  response = urllib.request.urlopen(response)  html = BeautifulSoup(response.read(), "html.parser", from_encoding='gbk')  return htmldef get_list(url, level=1, pid=0, get_level=2):  data = [];  level_arr = {'1': 'provincetr', '2': 'citytr', '3': 'countytr', '4': 'towntr', '5': 'villagetr'}  try:    print(url)    html = get_html(url)    c_url = url    tr_list = html.findAll('tr', {'class': level_arr[str(level)]})    for tr in tr_list:      region_name, href, page = '', '', ''      td_list = tr.findAll('td')      for td in td_list:        region_name = td.get_text();        # 判断是否存在该省份        if (level == 1):          sql = "select * from region where region_name='" + region_name + "'"          db.execute(sql)          exist = db.fetchone()          if(exist):continue        # 判断是否全数字-非法则跳过        if (region_name.isdigit()):          continue        if (region_name):          sql = "insert into region(region_name,pid,level,url) value('" + region_name + "','" + str(pid) + "','" + str(level) + "','" + url + "')"          db.execute(sql)          db.execute('SELECT LAST_INSERT_ID();')          last_id = db.fetchone()[0]        if (td.a):          page = td.a.attrs['href']          pattern = re.compile(r'\w*.html')          url = re.sub(pattern, page, c_url)          if (level <= get_level):get_list(url, level + 1, last_id)      # 每个省份执行完成，则提交      if (level == 1):        conn.commit()    return data;  except HTTPError as e:    # 如果有出错，则回滚    conn.rollback()    print(e) # HTTP Error 502: Proxy Errorurl = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/index.html'get_list(url)print('执行完成')

总结

以上就是这篇文章的全部内容了，希望本文的内容对大家的学习或者工作具有一定的参考学习价值，谢谢大家的支持。如果你想了解更多相关内容请查看下面相关链接