Python和Perl绘制中国北京跑步地图的方法

folder = u'D:/buptzym的同步盘/百度云/我的文档/数据分析/datasets/rungps/';
cookie='JSESSIONID=69DF607B71B1F14AFEC090F520B14B55; logincookie=5699607196$6098898D08E533587E82B33DD9D02196; persistent_cookie=5699607196$42C885AD38F59DCA407E09C95BE1A60B; uname_forloginform="buptzym@qq.com"; __utma=54733311.82935663.1447906150.1447937410.1456907433.7; __utmb=54733311.5.10.1456907433; __utmc=54733311; __utmz=54733311.1456907433.7.3.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; cookie_site=auto'
userid='5699607196';
f = codecs.open(folder + 'desert.htm', 'r', 'utf-8');
html = f.read();
f.close();
root = etree.HTML(html)
tree = etree.ElementTree(root);
listnode=tree.xpath('//*[@id="feedList"]');
numre=re.compile(u'骑行|跑步|公里|，|耗时|消耗|大卡');
urllists=[]
records=[];
for child in listnode[0].iterchildren():
record={};
temp=child.xpath('div[2]/div[1]/a[2]')
if len(temp)==0:
continue;
source= temp[0].attrib['href'];
record['id']=source.split('/')[-1];
info=temp[0].text;
numinfo= numre.split(info);
if len(numinfo)<6:
continue;
record['type']= info[0:2];
record['distance']= numinfo[1];
record['hot']=numinfo[6];
urllists.append('http://edooon.com/user/%s/record/export?type=gpx&id=%s' % (userid, record['id'])); 

opener = urllib.request.build_opener()
opener.addheaders.append(('Cookie', cookie));
path='//*[@id="exportList"]/li[1]/a';
for everyURL in urllists:
id = everyURL.split('=')[-1];
print(id);
url='http://edooon.com/user/%s/record/%s' % (userid, id);
f = opener.open(url);
html = f.read();
f.close();
root = etree.HTML(html)
tree = etree.ElementTree(root);
fs = str(tree.xpath(path)[0]);
if fs is None:
continue;
furl = 'http://edooon.com/user/%s/record/%s' % (userid, fs);
f = opener.open(furl);
html = f.read();
f.close();
filename=folder+'id'+'.gpx';
xmlfile = codecs.open(filename, 'wb');
xmlfile.write(html);
xmlfile.close(); 

def readgpx(x):
file= open(dir+x+'.gpx','r')
txt=file.read()
gpx=gpxpy.parse(txt)
mv=gpx.get_moving_data()
dat= {'移动时间':mv.moving_time,'静止时间':mv.stopped_time,'移动距离':mv.moving_distance,'暂停距离':mv.stopped_distance,'最大速度':mv.max_speed};
dat['总时间']=(gpx.get_duration())
dat['id']=str(x)
updown=gpx.get_uphill_downhill()
dat['上山']=(updown.uphill);
dat['下山']=(updown.downhill)
timebound=gpx.get_time_bounds();
dat['开始时间']=(timebound.start_time)
dat['结束时间']=(timebound.end_time)
p=gpx.get_points_data()[0]
dat['lat']=p.point.latitude
dat['lng']=p.point.longitude
file.close()
return dat 

def filtercity(r):
sp=r.split('/')[-1].split('.')
if sp[1]!='gpx':
return False;
if sp[0] in exceptids.values:
return False;
return True; 
bjids= [r for r in gpxs if filtercity(r)]