您好我从here
获得了以下模块import urllib
import urllib2
import json as j
import sys
__version__ = 0.242
def query(query, useragent='python-duckduckgo '+str(__version__), safesearch=True, html=False, meanings=True, **kwargs):
"""
Query DuckDuckGo, returning a Results object.
Here's a query that's unlikely to change:
>>> result = query('1 + 1')
>>> result.type
'nothing'
>>> result.answer.text
'1 + 1 = 2'
>>> result.answer.type
'calc'
Keword arguments:
useragent: UserAgent to use while querying. Default: "python-duckduckgo %d" (str)
safesearch: True for on, False for off. Default: True (bool)
html: True to allow HTML in output. Default: False (bool)
meanings: True to include disambiguations in results (bool)
Any other keyword arguments are passed directly to DuckDuckGo as URL params.
""" % __version__
safesearch = '1' if safesearch else '-1'
html = '0' if html else '1'
meanings = '0' if meanings else '1'
params = {
'q': query,
'o': 'json',
'kp': safesearch,
'no_redirect': '1',
'no_html': html,
'd': meanings,
}
params.update(kwargs)
encparams = urllib.urlencode(params)
url = 'http://api.duckduckgo.com/?' + encparams
request = urllib2.Request(url, headers={'User-Agent': useragent})
response = urllib2.urlopen(request)
json = j.loads(response.read())
response.close()
return Results(json)
class Results(object):
def __init__(self, json):
self.type = {'A': 'answer', 'D': 'disambiguation',
'C': 'category', 'N': 'name',
'E': 'exclusive', '': 'nothing'}.get(json.get('Type',''), '')
self.json = json
self.api_version = None # compat
self.heading = json.get('Heading', '')
self.results = [Result(elem) for elem in json.get('Results',[])]
self.related = [Result(elem) for elem in
json.get('RelatedTopics',[])]
self.abstract = Abstract(json)
self.redirect = Redirect(json)
self.definition = Definition(json)
self.answer = Answer(json)
self.image = Image({'Result':json.get('Image','')})
class Abstract(object):
def __init__(self, json):
self.html = json.get('Abstract', '')
self.text = json.get('AbstractText', '')
self.url = json.get('AbstractURL', '')
self.source = json.get('AbstractSource')
class Redirect(object):
def __init__(self, json):
self.url = json.get('Redirect', '')
class Result(object):
def __init__(self, json):
self.topics = json.get('Topics', [])
if self.topics:
self.topics = [Result(t) for t in self.topics]
return
self.html = json.get('Result')
self.text = json.get('Text')
self.url = json.get('FirstURL')
icon_json = json.get('Icon')
if icon_json is not None:
self.icon = Image(icon_json)
else:
self.icon = None
class Image(object):
def __init__(self, json):
self.url = json.get('Result')
self.height = json.get('Height', None)
self.width = json.get('Width', None)
class Answer(object):
def __init__(self, json):
self.text = json.get('Answer')
self.type = json.get('AnswerType', '')
class Definition(object):
def __init__(self, json):
self.text = json.get('Definition','')
self.url = json.get('DefinitionURL')
self.source = json.get('DefinitionSource')
def get_zci(q, web_fallback=True, priority=['answer', 'abstract', 'related.0', 'definition'], urls=True, **kwargs):
'''A helper method to get a single (and hopefully the best) ZCI result.
priority=list can be used to set the order in which fields will be checked for answers.
Use web_fallback=True to fall back to grabbing the first web result.
passed to query. This method will fall back to 'Sorry, no results.'
if it cannot find anything.'''
ddg = query('\\'+q, **kwargs)
response = ''
for p in priority:
ps = p.split('.')
type = ps[0]
index = int(ps[1]) if len(ps) > 1 else None
result = getattr(ddg, type)
if index is not None:
if not hasattr(result, '__getitem__'): raise TypeError('%s field is not indexable' % type)
result = result[index] if len(result) > index else None
if not result: continue
if result.text: response = result.text
if result.text and hasattr(result,'url') and urls:
if result.url: response += ' (%s)' % result.url
if response: break
# if there still isn't anything, try to get the first web result
if not response and web_fallback:
if ddg.redirect.url:
response = ddg.redirect.url
# final fallback
if not response:
response = 'Sorry, no results.'
return response
def main():
if len(sys.argv) > 1:
q = query(' '.join(sys.argv[1:]))
keys = q.json.keys()
keys.sort()
for key in keys:
sys.stdout.write(key)
if type(q.json[key]) in [str,unicode,int]: print(':', q.json[key])
else:
sys.stdout.write('\n')
for i in q.json[key]: print('\t',i)
else:
print('Usage: %s [query]' % sys.argv[0])
此代码似乎在python 2.7中正常工作但在3.4中我收到以下错误：
Traceback (most recent call last):
File "E:\Python34\My programs\Novos\duckduckgo.py", line 2, in <module>
import urllib2
ImportError: No module named 'urllib2'
我尝试使用2to3，但它给了我以下代码，它们也没有用：
import urllib.request, urllib.parse, urllib.error
import urllib.request, urllib.error, urllib.parse
import json as j
import sys
__version__ = 0.242
def query(query, useragent='python-duckduckgo '+str(__version__), safesearch=True, html=False, meanings=True, **kwargs):
"""
Query DuckDuckGo, returning a Results object.
Here's a query that's unlikely to change:
>>> result = query('1 + 1')
>>> result.type
'nothing'
>>> result.answer.text
'1 + 1 = 2'
>>> result.answer.type
'calc'
Keword arguments:
useragent: UserAgent to use while querying. Default: "python-duckduckgo %d" (str)
safesearch: True for on, False for off. Default: True (bool)
html: True to allow HTML in output. Default: False (bool)
meanings: True to include disambiguations in results (bool)
Any other keyword arguments are passed directly to DuckDuckGo as URL params.
""" % __version__
safesearch = '1' if safesearch else '-1'
html = '0' if html else '1'
meanings = '0' if meanings else '1'
params = {
'q': query,
'o': 'json',
'kp': safesearch,
'no_redirect': '1',
'no_html': html,
'd': meanings,
}
params.update(kwargs)
encparams = urllib.parse.urlencode(params)
url = 'http://api.duckduckgo.com/?' + encparams
request = urllib.request.Request(url, headers={'User-Agent': useragent})
response = urllib.request.urlopen(request)
json = j.loads(response.read())
response.close()
return Results(json)
class Results(object):
def __init__(self, json):
self.type = {'A': 'answer', 'D': 'disambiguation',
'C': 'category', 'N': 'name',
'E': 'exclusive', '': 'nothing'}.get(json.get('Type',''), '')
self.json = json
self.api_version = None # compat
self.heading = json.get('Heading', '')
self.results = [Result(elem) for elem in json.get('Results',[])]
self.related = [Result(elem) for elem in
json.get('RelatedTopics',[])]
self.abstract = Abstract(json)
self.redirect = Redirect(json)
self.definition = Definition(json)
self.answer = Answer(json)
self.image = Image({'Result':json.get('Image','')})
class Abstract(object):
def __init__(self, json):
self.html = json.get('Abstract', '')
self.text = json.get('AbstractText', '')
self.url = json.get('AbstractURL', '')
self.source = json.get('AbstractSource')
class Redirect(object):
def __init__(self, json):
self.url = json.get('Redirect', '')
class Result(object):
def __init__(self, json):
self.topics = json.get('Topics', [])
if self.topics:
self.topics = [Result(t) for t in self.topics]
return
self.html = json.get('Result')
self.text = json.get('Text')
self.url = json.get('FirstURL')
icon_json = json.get('Icon')
if icon_json is not None:
self.icon = Image(icon_json)
else:
self.icon = None
class Image(object):
def __init__(self, json):
self.url = json.get('Result')
self.height = json.get('Height', None)
self.width = json.get('Width', None)
class Answer(object):
def __init__(self, json):
self.text = json.get('Answer')
self.type = json.get('AnswerType', '')
class Definition(object):
def __init__(self, json):
self.text = json.get('Definition','')
self.url = json.get('DefinitionURL')
self.source = json.get('DefinitionSource')
def get_zci(q, web_fallback=True, priority=['answer', 'abstract', 'related.0', 'definition'], urls=True, **kwargs):
'''A helper method to get a single (and hopefully the best) ZCI result.
priority=list can be used to set the order in which fields will be checked for answers.
Use web_fallback=True to fall back to grabbing the first web result.
passed to query. This method will fall back to 'Sorry, no results.'
if it cannot find anything.'''
ddg = query('\\'+q, **kwargs)
response = ''
for p in priority:
ps = p.split('.')
type = ps[0]
index = int(ps[1]) if len(ps) > 1 else None
result = getattr(ddg, type)
if index is not None:
if not hasattr(result, '__getitem__'): raise TypeError('%s field is not indexable' % type)
result = result[index] if len(result) > index else None
if not result: continue
if result.text: response = result.text
if result.text and hasattr(result,'url') and urls:
if result.url: response += ' (%s)' % result.url
if response: break
# if there still isn't anything, try to get the first web result
if not response and web_fallback:
if ddg.redirect.url:
response = ddg.redirect.url
# final fallback
if not response:
response = 'Sorry, no results.'
return response
def main():
if len(sys.argv) > 1:
q = query(' '.join(sys.argv[1:]))
keys = list(q.json.keys())
keys.sort()
for key in keys:
sys.stdout.write(key)
if type(q.json[key]) in [str,str,int]: print((':', q.json[key]))
else:
sys.stdout.write('\n')
for i in q.json[key]: print(('\t',i))
else:
print(('Usage: %s [query]' % sys.argv[0]))
就在您运行查询功能时，您知道第二个代码段给了我以下错误：
Traceback (most recent call last):
File "<pyshell#1>", line 1, in <module>
query("foobar")
File "E:\Python34\duckduckgo.py", line 45, in query
json = j.loads(response.read())
File "E:\Python34\lib\json\__init__.py", line 312, in loads
s.__class__.__name__))
TypeError: the JSON object must be str, not 'bytes'
所以有人能告诉我这里做错了吗？
提前致谢！
答案 0 :(得分：2)
嗯，我自己发现了它的灵魂。
将代码转换为python 3后，要解决TypeError: the JSON object must be str, not 'bytes'错误，请替换
json = j.loads(response.read())`
与`
reader = codecs.getreader("utf-8")
json = j.loads(reader(response).read())`
并在代码顶部添加import codecs。
这个修复就像一个魅力！