Bing supports mp3s and example.

src/fastwq/service/bing.py

@@ -1,11 +1,10 @@
 #-*- coding:utf-8 -*-
 import re
-
-from aqt.utils import showInfo, showText
 from .base import WebService, export, register, with_styles, parseHtml
 
+bing_download_mp3 = True
 
-@register([u'必应', u'Bing'])
+@register([u'Bing', u'Bing'])
 class Bing(WebService):
 
     def __init__(self):
@@ -16,54 +15,113 @@ class Bing(WebService):
         data = self.get_response(u"http://cn.bing.com/dict/search?q={}&mkt=zh-cn".format(word))
         soup = parseHtml(data)
         result = {
-            'phonitic_us': '',
+            'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
-            'phonitic_uk': '',
-            'participle': '',
             'def': '',
+            'sams': '',
         }
 
-        element = soup.find('div', class_='hd_prUS')
+        #音
+        element = soup.find('div', class_='hd_tf_lh')
         if element:
-            result['phonitic_us'] = str(element).decode('utf-8')
+            audios = element.find_all('a')
+            #美式英标
+            tag = element.find('div', class_='hd_pr')
+            if tag:
+                result['pronunciation']['AmE'] = str(tag).decode('utf-8')
+                #美音
+                if audios:
+                    tag = audios[0]
+                    audio_url = tag.get('onclick')
+                    if audio_url:
+                        result['pronunciation']['AmEmp3'] = u''.join(re.findall(r'https://.*\.mp3', audio_url))
 
-        element = soup.find('div', class_='hd_pr')
+            #英式音标
-        if element:
+            tag = element.find('div', class_='hd_prUS')
-            result['phonitic_uk'] = str(element).decode('utf-8')
+            if tag:
-
+                result['pronunciation']['BrE'] = str(tag).decode('utf-8')
-        element = soup.find('div', class_='hd_if')
+                #英音
-        if element:
+                if audios:
-            result['participle'] = str(element).decode('utf-8')
+                    tag = audios[1]
+                    audio_url = tag.get('onclick')
+                    if audio_url:
+                        result['pronunciation']['BrEmp3'] = u''.join(re.findall(r'https://.*\.mp3', audio_url))
 
+        #释义
         element = soup.find('div', class_='qdef')
         if element:
             element = getattr(element, 'ul', '')
             if element:
                 result['def'] = u''.join([str(content) for content in element.contents])
 
+        #例句 
+        element = soup.find('div', id='sentenceSeg')
+        if element:
+            #英文例句
+            tags = element.find_all('div', {"class": 'sen_en'})
+            result['sams'] = [{'eng': u''.join(tag.find_all(text=True))} for tag in tags]
+            #例句翻译
+            tags = element.find_all('div', {"class": 'sen_cn'})
+            for i, tag in enumerate(tags):
+                result['sams'][i]['chn'] = u''.join(tag.find_all(text=True))
+
         return self.cache_this(result)
 
     def _get_field(self, key, default=u''):
         return self.cache_result(key) if self.cached(key) else self._get_content().get(key, default)
 
-    @export('AME_PHON', 1)
-    def fld_phonetic_us(self):
-        return self._get_field('phonitic_us')
-
-    @export('BRE_PHON', 2)
-    def fld_phonetic_uk(self):
-        return self._get_field('phonitic_uk')
-
-    @export([u'词语时态', u'Participle'], 3)
-    def fld_participle(self):
-        return self._get_field('participle')
-
     @with_styles(css='.pos{font-weight:bold;margin-right:4px;}', need_wrap_css=True, wrap_class='bing')
     def _css(self, val):
         return val
+
+    @export('AME_PHON', 1)
+    def fld_phonetic_us(self):
+        seg = self._get_field('pronunciation')
+        return seg.get('AmE', u'')
+
+    @export('BRE_PHON', 2)
+    def fld_phonetic_uk(self):
+        seg = self._get_field('pronunciation')
+        return seg.get('BrE', u'')
+
+    def _fld_mp3(self, fld):
+        audio_url = self._get_field('pronunciation')[fld]
+        if bing_download_mp3 and audio_url:
+            filename = u''.join(re.findall(r'\w*\.mp3', audio_url))
+            if filename and self.download(audio_url, filename):
+                return self.get_anki_label(u'bing_{0}_{1}'.format(fld, filename), 'audio')
+        return ''
+
+    @export('AME_PRON', 3)
+    def fld_mp3_us(self):
+        return self._fld_mp3('AmEmp3')
+
+    @export('BRE_PRON', 4)
+    def fld_mp3_uk(self):
+        return self._fld_mp3('BrEmp3')
     
-    @export('DEF', 4)
+    @export('DEF', 5)
     def fld_definition(self):
         val = self._get_field('def')
         if val == None or val == '':
             return ''
         return self._css(val)
+
+    @export('EXAMPLE', 6)
+    def fld_samples(self):
+        max_numbers = 10
+        segs = self._get_field('sams')
+        sentences = ''
+        for i, seg in enumerate(segs):
+            sentences += u"""<li><div class="se_li1">
+                            <div class="sen_en">{0}.{1}</div>
+                            <div class="sen_cn">{2}</div>
+                        </div></li>""".format(i+1, seg['eng'], seg['chn'])
+            if i == 9:
+                break
+        if sentences:
+            return u"""<div class="se_div">
+                            <div class="sentenceCon">
+                                <div id="sentenceSeg"><ol>{0}</ol></div>
+                            </div>
+                    </div>""".format(sentences)
+        return ''