Merge pull request #39 from patzzz/img-cambridge

Download images and thumbnails from Cambridge

addons/fastwq/service/dict/cambridge.py

@@ -2,7 +2,9 @@
 import os
 from ..base import *
 
+cambridge_url_base = u'https://dictionary.cambridge.org'
 cambridge_download_mp3 = True
+cambridge_download_img = True
 
 @register([u'剑桥英英', u'Cambridge'])
 class Cambridge(WebService):
@@ -11,12 +13,13 @@ class Cambridge(WebService):
         super(Cambridge, self).__init__()
 
     def _get_from_api(self):
-        data = self.get_response(u"https://dictionary.cambridge.org/dictionary/english/{}".format(self.quote_word))
+        data = self.get_response(u'{0}/dictionary/english/{1}'.format(cambridge_url_base, self.quote_word))
         soup = parse_html(data)
         result = {
             'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
-            'def': '',
+            'image': '',
-            'sams': '',
+            'thumb': '',
+            'def': ''
         }
 
         #页
@@ -35,7 +38,7 @@ class Cambridge(WebService):
                         result['pronunciation'][pn] = str(p.get_text()).decode('utf-8') if p else u''
                         snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
                         if snd:
-                            result['pronunciation'][pn+'mp3'] = u'https://dictionary.cambridge.org' + snd.get('data-src-mp3')
+                            result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3')
             #义
             body = element.find('div', class_='pos-body')
             if body:
@@ -56,6 +59,10 @@ class Cambridge(WebService):
                             )
                         )
                     result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>'
+                img = body.find('img', class_='lightboxLink')
+                if img:
+                    result['image'] = cambridge_url_base + img.get('data-image')
+                    result['thumb'] = cambridge_url_base + img.get('src')
 
         return self.cache_this(result)
 
@@ -73,6 +80,14 @@ class Cambridge(WebService):
         seg = self._get_field('pronunciation')
         return seg.get('BrE', u'') if seg else u''
 
+    def _fld_img(self, fld):
+        image_url = self._get_field(fld)
+        if cambridge_download_img and image_url:
+            filename = get_hex_name(self.unique.lower(), image_url, 'jpg')
+            if os.path.exists(filename) or self.net_download(filename, image_url):
+                return self.get_anki_label(filename, 'img')
+        return ''
+
     def _fld_mp3(self, fld):
         audio_url = self._get_field('pronunciation')[fld]
         if cambridge_download_mp3 and audio_url:
@@ -81,6 +96,14 @@ class Cambridge(WebService):
                 return self.get_anki_label(filename, 'audio')
         return ''
 
+    @export('IMAGE')
+    def fld_image(self):
+        return self._fld_img('image')
+
+    @export(u'Thumbnails')
+    def fld_thumbnail(self):
+        return self._fld_img('thumb')
+
     @export('AME_PRON')
     def fld_mp3_us(self):
         return self._fld_mp3('AmEmp3')

addons21/fastwq/service/dict/cambridge.py

@@ -2,7 +2,9 @@
 import os
 from ..base import *
 
+cambridge_url_base = u'https://dictionary.cambridge.org'
 cambridge_download_mp3 = True
+cambridge_download_img = True
 
 @register([u'剑桥英英', u'Cambridge'])
 class Cambridge(WebService):
@@ -11,12 +13,13 @@ class Cambridge(WebService):
         super(Cambridge, self).__init__()
 
     def _get_from_api(self):
-        data = self.get_response(u"https://dictionary.cambridge.org/dictionary/english/{}".format(self.quote_word))
+        data = self.get_response(u'{0}/dictionary/english/{1}'.format(cambridge_url_base, self.quote_word))
         soup = parse_html(data)
         result = {
             'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
-            'def': '',
+            'image': '',
-            'sams': '',
+            'thumb': '',
+            'def': ''
         }
 
         #页
@@ -35,7 +38,7 @@ class Cambridge(WebService):
                         result['pronunciation'][pn] = p.get_text() if p else u''
                         snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
                         if snd:
-                            result['pronunciation'][pn+'mp3'] = u'https://dictionary.cambridge.org' + snd.get('data-src-mp3')
+                            result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3')
             #义
             body = element.find('div', class_='pos-body')
             if body:
@@ -56,6 +59,10 @@ class Cambridge(WebService):
                             )
                         )
                     result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>'
+                img = body.find('img', class_='lightboxLink')
+                if img:
+                    result['image'] = cambridge_url_base + img.get('data-image')
+                    result['thumb'] = cambridge_url_base + img.get('src')
 
         return self.cache_this(result)
 
@@ -73,6 +80,14 @@ class Cambridge(WebService):
         seg = self._get_field('pronunciation')
         return seg.get('BrE', u'') if seg else u''
 
+    def _fld_img(self, fld):
+        image_url = self._get_field(fld)
+        if cambridge_download_img and image_url:
+            filename = get_hex_name(self.unique.lower(), image_url, 'jpg')
+            if os.path.exists(filename) or self.net_download(filename, image_url):
+                return self.get_anki_label(filename, 'img')
+        return ''
+
     def _fld_mp3(self, fld):
         audio_url = self._get_field('pronunciation')[fld]
         if cambridge_download_mp3 and audio_url:
@@ -81,6 +96,14 @@ class Cambridge(WebService):
                 return self.get_anki_label(filename, 'audio')
         return ''
 
+    @export('IMAGE')
+    def fld_image(self):
+        return self._fld_img('image')
+
+    @export(u'Thumbnails')
+    def fld_thumbnail(self):
+        return self._fld_img('thumb')
+
     @export('AME_PRON')
     def fld_mp3_us(self):
         return self._fld_mp3('AmEmp3')