无法从服务器获取搜索结果：使用Python的Facebook Graph API

Question

我在自己做一些简单的Python和Facebook Graph的练习时，遇到了一个奇怪的问题：

import time
import sys
import urllib2
import urllib
from json import loads

base_url = "https://graph.facebook.com/search?q="
post_id = None
post_type = None
user_id = None 
message = None
created_time = None

def doit(hour):
    page = 1
    search_term = "\"Plastic Planet\""
    encoded_search_term = urllib.quote(search_term)
    print encoded_search_term
    type="&type=post"
    url = "%s%s%s" % (base_url,encoded_search_term,type)
    print url
    while(1):

        try:
            response = urllib2.urlopen(url)
        except urllib2.HTTPError, e:
            print e
        finally:
            pass   

        content = response.read()
        content = loads(content)

        print "=================================="
        for c in content["data"]:
            print c
            print "****************************************"

        try:
            content["paging"]
            print "current URL"
            print url
            print "next page!------------"
            url = content["paging"]["next"]
            print url
        except:
            pass
        finally:
            pass

        """
        print "new URL is ======================="
        print url
        print "==================================" 
        """
        print url

我想要做的是自动翻页查看搜索结果，试着用content["paging"]["next"]来获取下一页的内容。

但奇怪的是，没有返回任何数据；我收到的是以下内容：

{"data":[]}

即使在第一次循环的时候也是这样。

不过当我把这个网址复制到浏览器里时，却能返回很多结果。

我还试过用我的访问令牌，但结果还是一样。

+++++++++++++++++++已编辑和简化++++++++++++++++++

感谢TryPyPy，这里是我之前问题的简化和编辑版本：

为什么会出现：

   import urllib2
       url = "https://graph.facebook.com/searchq=%22Plastic+Planet%22&type=post&limit=25&until=2010-12-29T19%3A54%3A56%2B0000"
       response = urllib2.urlopen(url)
       print response.read() 

结果是{"data":[]}？

但同样的网址在浏览器中却能产生很多数据？

Answer 1

我在使用Chrome（得到了很多数据）和Firefox（得到了空响应）进行反复尝试后，发现问题主要出在'Accept-Language'这个请求头上。其他的修改应该只是表面上的变化，但我对CookieJar的情况不太确定。

import time
import sys
import urllib2
import urllib
from json import loads
import cookielib

base_url = "https://graph.facebook.com/search?q="
post_id = None
post_type = None
user_id = None 
message = None
created_time = None

jar = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(jar))
opener.addheaders = [
    ('Accept-Language', 'en-US,en;q=0.8'),]

def doit(hour):
    page = 1
    search_term = "\"Plastic Planet\""
    encoded_search_term = urllib.quote(search_term)
    print encoded_search_term
    type="&type=post"
    url = "%s%s%s" % (base_url,encoded_search_term,type)

    print url

    data = True
    while data:
        response = opener.open(url)
        opener.addheaders += [
            ('Referer', url) ]

        content = response.read()
        content = loads(content)

        print "=================================="
        for c in content["data"]:
            print c.keys()
        print "****************************************"

        if "paging" in content:
            print "current URL"
            print url
            print "next page!------------"
            url = content["paging"]["next"]
            print url
        else:
            print content
            print url
            data = False

doit(1)

这是一个简化过的、能正常工作的版本：

import urllib2
import urllib
from json import loads
import cookielib

def doit(search_term, base_url = "https://graph.facebook.com/search?q="):
    opener = urllib2.build_opener()
    opener.addheaders = [('Accept-Language', 'en-US,en;q=0.8')]

    encoded_search_term = urllib.quote(search_term)
    type="&type=post"
    url = "%s%s%s" % (base_url,encoded_search_term,type)

    print encoded_search_term
    print url

    data = True
    while data:
        response = opener.open(url)

        content = loads(response.read())

        print "=================================="
        for c in content["data"]:
            print c.keys()
        print "****************************************"

        if "paging" in content:
            url = content["paging"]["next"]
        else:
            print "Empty response"
            print content
            data = False

doit('"Plastic Planet"')