查询许久，最终选择一个，之前一直py3.6不成功，换了2.7就好多了。如果有重复去下重即可。
这里面非常重要的基类对象的init()方法与超类方法，将在下面进行记录。# -*- coding:utf-8 -*-import jsonimport urllib2import sysimport impimport time#显示当前系统编码print(sys.getdefaultencoding())#修改编码：py3.6无法解析百度地图API,如有人解决imp.reload(sys)
sys.setdefaultencoding('utf-8')#对百度api进行解析class BaiDuPOI(object):
def __init__(self,itemy,loc):
self.itemy = itemy
self.loc = loc#对页数进行循环提取
def urls(self):
api_key = baidu_api
urls = [] for pages in range(0,20):
url = 'http://api.map.baidu.com/place/v2/search?query=' 5A&景区 '&bounds=' + self.loc +'&page_size=20&page_num=' + str(pages) + '&output=json&ak=' + api_key
urls.append(url) return urls#获取json数据
def baidu_search(self):
json_sel = ["name,lat,lng"] for url in self.urls():
json_obj = urllib2.urlopen(url)
data = json.load(json_obj)
for item in data['results']:
jname = item["name"]
jlat = item["location"]["lat"]
jlng = item["location"]["lng"]
js_sel = jname +',' + str(jlat) + ',' + str(jlng)
json_sel.append(js_sel) return json_sel#对数据进行关键词提取与写入if __name__ == '__main__':
baidu_api = '133d5d0ef4fcc60f7ff63a76f5b538ac' #这里填入你的百度API
print "开始爬数据，请稍等..."
start_time = time.time()
locs_to_use = ['39.0,116.0,39.05,116.05'] for loc_to_use in locs_to_use:
par = BaiDuPOI(u'景区',loc_to_use) #请修改这里的参数
a = par.baidu_search()
doc = open('baidu_csv.csv','w') for ax in a:
doc.write(ax)
doc.write('n')
doc.close
end_time = time.time() print "数据爬取完毕，用时%.2f秒" % (end_time - start_time)
参考文献：http://www.workloadup.com/baidupoi.html
