首页 > 编程语言 > 详细

python爬虫1.4

时间:2017-10-18 23:42:12      阅读:344      评论:0      收藏:0      [点我收藏+]
import requests
import time
import xml.etree.ElementTree as ET

from multiprocessing.dummy import Pool as ThreadPoo;
from xml.parsers.expat import ParserCreate

class DefaultSaxHandler(object):
    def __init__(self, provinces):
        self.provinces = provinces

    def start_element(self, name, attrs):
        if name != map:
            name = attrs[title]
            number = attrs[href]
            self.provinces.append((name, number))
            
    def end_element(self, name):
        pass

    def char_data(self, text):
        pass
    
def get_provinces(url):
    content = requests.get(url).content.decode(gb2312)
    start = content.find(<map name=\"map_86\" id=\"map_86\">)
    end = content.find(</map>)
    content = content[start:end + len(</map>)].strip()
    print(content)
    provinces = []
    handler = DefaultSaxHandler(provinces)
    parser = ParserCreate()
    parser.StartElementHandler = handler.start_element
    parser.EndElementHandler = handler.end_element
    parser.CharacterDataHandler = handler.char_data
    parser.Parse(content)
    return provinces

provinces = get_provinces(http://www.ip138.com/post)
print(provinces)

 

python爬虫1.4

原文:http://www.cnblogs.com/xiaoyingying/p/7689841.html

(0)
(0)
   
举报
评论 一句话评论(0
关于我们 - 联系我们 - 留言反馈 - 联系我们:wmxa8@hotmail.com
© 2014 bubuko.com 版权所有
打开技术之扣,分享程序人生!