我试图从nominatim到geo-code几千个城市得到响应。Xml从网络响应中解析
import os
import requests
import xml.etree.ElementTree as ET
txt = open('input.txt', 'r').readlines()
for line in txt:
lp, region, district, municipality, city = line.split('\t')
baseUrl = 'http://nominatim.openstreetmap.org/search/gb/'+region+'/'+district+'/'+municipality+'/'+city+'/?format=xml'
# eg. http://nominatim.openstreetmap.org/search/pl/podkarpackie/stalowowolski/Bojan%C3%B3w/Zapu%C5%9Bcie/?format=xml
resp = requests.get(baseUrl)
resp.encoding = 'UTF-8' # special diacritics
msg = resp.text
# parse response to get lat & long
tree = ET.parse(msg)
root = tree.getroot()
print tree
但结果是:
Traceback (most recent call last):
File "geo_miasta.py", line 17, in <module>
tree = ET.parse(msg)
File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1182, in parse
tree.parse(source, parser)
File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 647, in parse
source = open(source, "rb")
IOError: [Errno 2] No such file or directory: u'<?xml version="1.0" encoding="UTF-8" ?>\n<searchresults timestamp=\'Tue, 11 Feb 14 21:13:50 +0000\' attribution=\'Data \xa9 OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright\' querystring=\'\u015awierczyna, Drzewica, opoczy\u0144ski, \u0142\xf3dzkie, gb\' polygon=\'false\' more_url=\'http://nominatim.openstreetmap.org/search?format=xml&exclude_place_ids=&q=%C5%9Awierczyna%2C+Drzewica%2C+opoczy%C5%84ski%2C+%C5%82%C3%B3dzkie%2C+gb\'>\n</searchresults>'
有什么不对呢?
编辑: 吴丹到@rob我的解决方案是:
#! /usr/bin/env python2.7
# -*- coding: utf-8 -*-
import os
import requests
import xml.etree.ElementTree as ET
txt = open('input.txt', 'r').read().split('\n')
for line in txt:
lp, region, district, municipality, city = line.split('\t')
baseUrl = 'http://nominatim.openstreetmap.org/search/pl/'+region+'/'+district+'/'+municipality+'/'+city+'/?format=xml'
resp = requests.get(baseUrl)
msg = resp.content
tree = ET.fromstring(msg)
for place in tree.findall('place'):
location = '{:5f}\t{:5f}'.format(
float(place.get('lat')),
float(place.get('lon')))
f = open('result.txt', 'a')
f.write(location+'\t'+region+'\t'+district+'\t'+municipality+'\t'+city)
f.close()
谢谢,这个移动的错误边境编码空间:'UnicodeEncodeError: 'ASCII' 编解码器” t在位置115编码字符u'\ xa9':序号不在范围内(128)' – m93
@ m93 - 这是因为您正在使用'resp.text'而不是'resp.content'。看到我的编辑完整的程序,应该让你开始。 –
你说得对。这个示例有效。谢谢。 – m93