Foundations of Python Network Programing，Third Edition 《python网络编程》，本书中的代码可在Github上搜索fopnp下载
本书的第一章中使用到了google地图的api来获取一个地址的经度和纬度，因为众所周知的原因会出现无法访问，我们需要使用代理访问
因此书上的代码需要根据实际情况来修改，我的电脑的代理地址为127.0.0.1:1080，下面放我的代码吧，可根据自己电脑的代理设置进行修改。
运行环境：Windows 10,Anaconda3,python3.6.3,Pycharm Edu 2017.3
调用库：
#search1.py from pygeocoder import Geocoder if __name__ == '__main__':
a = Geocoder()
a.proxy = "127.0.0.1:1080"
address = '207 N. Definace St,Archbold,OH'
print(a.geocode(address)[0].coordinates)
这里使用的是Geocoder中的proxy参数设置代理（需要先使用pip安装pygeocoder），因此必须先实例化，不能像书中一样直接print
应用层：
#search2.py
import requests
proxies = {"http": "http://127.0.0.1:1080", "https": "http://127.0.0.1:1080", }
def geocode(address):
parameters = {'address': address, 'sensor': 'falise'}
base = 'http://maps.googleapis.com/maps/api/geocode/json'
response = requests.get(base, params=parameters, proxies=proxies)
answer = response.json()
print(answer['results'][0]['geometry']['location'])
if __name__ == '__main__':
geocode('207 N. Defiance St,Archbold, OH')
这里使用了requests中的proxies参数设置代理
使用HTTP协议：
# search3.py import http.client
import json
from urllib.parse import quote_plus base = '/maps/api/geocode/json' def geocode(address):
path = '{}?address={}&sensor=false'.format(base, quote_plus(address))
connection = http.client.HTTPSConnection('127.0.0.1', 1080)
connection.set_tunnel('map.google.com')
connection.request('GET', path)
rawreply = connection.getresponse().read()
reply = json.loads(rawreply.decode('utf-8'))
print(reply['results'][0]['geometry']['location']) if __name__ == '__main__':
geocode('207 N. Defiance St,Archbold, OH')
这里会提示
Traceback (most recent call last):
File "E:/Learn Python/Python网络编程/search3.py", line 21, in <module>
geocode('207 N. Defiance St,Archbold, OH')
File "E:/Learn Python/Python网络编程/search3.py", line 16, in geocode
reply = json.loads(rawreply.decode('utf-8'))
File "D:\Anaconda3\lib\json\__init__.py", line 354, in loads
return _default_decoder.decode(s)
File "D:\Anaconda3\lib\json\decoder.py", line 339, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "D:\Anaconda3\lib\json\decoder.py", line 357, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Process finished with exit code 1
很明显报了一个json.decoder.JSONDecodeError的错误 说明没有能够正确访问，json decode失败
print(rawreply)发现rawreply返回的是这样的html文件
b'<HTML><HEAD><meta http-equiv="content-type" content="text/html;charset=utf-8">\n
<TITLE>301 Moved</TITLE></HEAD><BODY>\n<H1>301 Moved</H1>\n
The document has moved\n
<A HREF="https://maps.google.com/maps/api/geocode/json?address=207+N.+Defiance+St%2CArchbold%2C+OH&sensor=false">here</A>.\r\n
</BODY>
</HTML>
\r\n'
返回了一个301错误，说明需要重定向这里我们使用的是HTTPS协议因此不会像浏览器一样直接重定向，感觉应该是google反爬虫的一种行为
因此我们使用正则表达式提取字符串（方法来自https://www.cnblogs.com/rj81/p/5933838.html），更改后代码如下
# search3.py import http.client
import json
from urllib.parse import quote_plus
import re base = '/maps/api/geocode/json' def geocode(address):
path = '{}?address={}&sensor=false'.format(base, quote_plus(address))
connection = http.client.HTTPSConnection('127.0.0.1', 1080)
connection.set_tunnel('map.google.com')
connection.request('GET', path)
rawreply = connection.getresponse().read().decode()
newweb = re.findall(r"HREF=\"(.+?)\"", string=rawreply)
# print(newweb)
connection.request('GET', newweb[0])
rawreply = connection.getresponse().read()
# print(path)
# print(rawreply)
reply = json.loads(rawreply.decode('utf-8'))
print(reply['results'][0]['geometry']['location']) if __name__ == '__main__':
geocode('207 N. Defiance St, Archbold, OH')
即可正确输出结果
{'lat': 41.5219645, 'lng': -84.3066496}
Process finished with exit code 0
这里需要注意的是 我一开始以为newweb是一个str，直接使用了connection.request('GET', newweb)
结果发现AttributeError: 'list' object has no attribute 'startswith'的错误，更改之后即可正常输出
直接使用Socket与谷歌地图通信：
设置代理的方法（转自http://www.jb51.net/article/50510.htm）
urllib2：
proxy_handler = urllib2.ProxyHandler({'http' : 'http://地址:端口'})
opener = urllib2.build_opener(proxy_handler, urllib2.HTTPHandler)
urllib2.install_opener(opener)
socket：
import socks, socket
socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "地址", 端口)
socket.socket = socks.socksocket
代码如下：
#search4.py
#!/usr/bin/env python3 import socket
import socks
from urllib.parse import quote_plus request_text = """\
GET /maps/api/geocode/json?address={}&sensor=false HTTP/1.1\r\n\
Host: maps.google.com:80\r\n\
User-Agent: search4.py (Foundations of Python Network Programming)\r\n\
Connection: close\r\n\
\r\n\
""" def geocode(address):
socks.set_default_proxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 1080)
socket.socket = socks.socksocket
sock = socket.socket()
sock.connect(('maps.google.com', 80))
request = request_text.format(quote_plus(address))
sock.sendall(request.encode('ascii'))
raw_reply = b''
while True:
more = sock.recv(4096)
if not more:
break
raw_reply += more
print(raw_reply.decode('utf-8')) if __name__ == '__main__':
geocode('207 N. Defiance St, Archbold, OH')
运行输出：
HTTP/1.1 OK
Content-Type: application/json; charset=UTF-
Date: Fri, Jan :: GMT
Expires: Sat, Jan :: GMT
Cache-Control: public, max-age=
Access-Control-Allow-Origin: *
Server: mafe
X-XSS-Protection: ; mode=block
X-Frame-Options: SAMEORIGIN
Accept-Ranges: none
Vary: Accept-Language,Accept-Encoding
Connection: close {
"results" : [
{
"address_components" : [
{
"long_name" : "",
"short_name" : "",
"types" : [ "street_number" ]
},
{
"long_name" : "North Defiance Street",
"short_name" : "N Defiance St",
"types" : [ "route" ]
},
{
"long_name" : "Archbold",
"short_name" : "Archbold",
"types" : [ "locality", "political" ]
},
{
"long_name" : "German Township",
"short_name" : "German Township",
"types" : [ "administrative_area_level_3", "political" ]
},
{
"long_name" : "Fulton County",
"short_name" : "Fulton County",
"types" : [ "administrative_area_level_2", "political" ]
},
{
"long_name" : "Ohio",
"short_name" : "OH",
"types" : [ "administrative_area_level_1", "political" ]
},
{
"long_name" : "United States",
"short_name" : "US",
"types" : [ "country", "political" ]
},
{
"long_name" : "",
"short_name" : "",
"types" : [ "postal_code" ]
},
{
"long_name" : "",
"short_name" : "",
"types" : [ "postal_code_suffix" ]
}
],
"formatted_address" : "207 N Defiance St, Archbold, OH 43502, USA",
"geometry" : {
"bounds" : {
"northeast" : {
"lat" : 41.521994,
"lng" : -84.30646179999999
},
"southwest" : {
"lat" : 41.521935,
"lng" : -84.30683739999999
}
},
"location" : {
"lat" : 41.5219645,
"lng" : -84.3066496
},
"location_type" : "ROOFTOP",
"viewport" : {
"northeast" : {
"lat" : 41.5233134802915,
"lng" : -84.30530061970849
},
"southwest" : {
"lat" : 41.5206155197085,
"lng" : -84.3079985802915
}
}
},
"place_id" : "ChIJk4BHnIy0PYgRXbKj5GjFe_U",
"types" : [ "premise" ]
}
],
"status" : "OK"
} Process finished with exit code 0