无法从服务器端检索搜索结果：使用Python的Facebook Graph API

Posted 2021-03-30

我正在自己做一些简单的Python + FB Graph训练，我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

我在这里要做的是自动翻阅搜索结果，但尝试内容[“分页”] [“下一步”]

但奇怪的是没有数据返回;我收到以下内容：

{"data":[]}

即使是在第一个循环中。

但是当我将URL复制到浏览器中时，返回了很多结果。

我也试过一个带有访问令牌的版本，同样的事情发生了。

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

好的，多亏了TryPyPy，这是我上一个问题的简化和编辑版本：

这是为什么：

   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() 

导致{"data":[]}？

但是同一个url会在浏览器中产生大量数据吗？

答案

使用Chrome（我获得大量数据）和Firefox（我获得空响应）的试验和错误使我在'Accept-Language'标题上为零。其他修改据说只是装饰性的，但我不确定CookieJar。

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)

这是一个清理过的最小工作版本：

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"')