ouczbs/anki-word-query
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Download images and thumbnails from Cambridge

Browse Source
This commit is contained in:
Patrizia 2018-08-19 14:50:00 +02:00
parent de1851fc6d
commit dbf1fd096c
2 changed files with 58 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
addons/fastwq/service/dict/cambridge.py
View File

@ -2,7 +2,9 @@
import os import os
from ..base import * from ..base import *
cambridge_url_base = u'https://dictionary.cambridge.org'
cambridge_download_mp3 = True cambridge_download_mp3 = True
cambridge_download_img = True
@register([u'剑桥英英', u'Cambridge']) @register([u'剑桥英英', u'Cambridge'])
class Cambridge(WebService): class Cambridge(WebService):
@ -11,12 +13,13 @@ class Cambridge(WebService):
super(Cambridge, self).__init__() super(Cambridge, self).__init__()
def _get_from_api(self): 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) soup = parse_html(data)
result = { result = {
'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''}, 'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
'def': '', 'image': '',
'sams': '', 'thumb': '',
'def': ''
} }
#页 #页
@ -35,7 +38,7 @@ class Cambridge(WebService):
result['pronunciation'][pn] = str(p.get_text()).decode('utf-8') if p else u'' 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') snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
if snd: 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 #义
body = element.find('div', class_='pos-body') body = element.find('div', class_='pos-body')
if body: if body:
@ -56,9 +59,13 @@ class Cambridge(WebService):
) )
) )
result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>' 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) return self.cache_this(result)
@with_styles(need_wrap_css=True, cssfile='_cambridge.css') @with_styles(need_wrap_css=True, cssfile='_cambridge.css')
def _css(self, val): def _css(self, val):
return val return val
@ -73,6 +80,14 @@ class Cambridge(WebService):
seg = self._get_field('pronunciation') seg = self._get_field('pronunciation')
return seg.get('BrE', u'') if seg else u'' 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): def _fld_mp3(self, fld):
audio_url = self._get_field('pronunciation')[fld] audio_url = self._get_field('pronunciation')[fld]
if cambridge_download_mp3 and audio_url: if cambridge_download_mp3 and audio_url:
@ -81,6 +96,14 @@ class Cambridge(WebService):
return self.get_anki_label(filename, 'audio') return self.get_anki_label(filename, 'audio')
return '' 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') @export('AME_PRON')
def fld_mp3_us(self): def fld_mp3_us(self):
return self._fld_mp3('AmEmp3') return self._fld_mp3('AmEmp3')
@ -88,7 +111,7 @@ class Cambridge(WebService):
@export('BRE_PRON') @export('BRE_PRON')
def fld_mp3_uk(self): def fld_mp3_uk(self):
return self._fld_mp3('BrEmp3') return self._fld_mp3('BrEmp3')
@export('DEF') @export('DEF')
def fld_definition(self): def fld_definition(self):
val = self._get_field('def') val = self._get_field('def')

35
addons21/fastwq/service/dict/cambridge.py
View File

@ -2,7 +2,9 @@
import os import os
from ..base import * from ..base import *
cambridge_url_base = u'https://dictionary.cambridge.org'
cambridge_download_mp3 = True cambridge_download_mp3 = True
cambridge_download_img = True
@register([u'剑桥英英', u'Cambridge']) @register([u'剑桥英英', u'Cambridge'])
class Cambridge(WebService): class Cambridge(WebService):
@ -11,12 +13,13 @@ class Cambridge(WebService):
super(Cambridge, self).__init__() super(Cambridge, self).__init__()
def _get_from_api(self): 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) soup = parse_html(data)
result = { result = {
'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''}, 'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
'def': '', 'image': '',
'sams': '', 'thumb': '',
'def': ''
} }
#页 #页
@ -35,7 +38,7 @@ class Cambridge(WebService):
result['pronunciation'][pn] = p.get_text() if p else u'' result['pronunciation'][pn] = p.get_text() if p else u''
snd = tag.find('span', class_='circle circle-btn sound audio_play_button') snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
if snd: 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 #义
body = element.find('div', class_='pos-body') body = element.find('div', class_='pos-body')
if body: if body:
@ -56,9 +59,13 @@ class Cambridge(WebService):
) )
) )
result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>' 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) return self.cache_this(result)
@with_styles(need_wrap_css=True, cssfile='_cambridge.css') @with_styles(need_wrap_css=True, cssfile='_cambridge.css')
def _css(self, val): def _css(self, val):
return val return val
@ -73,6 +80,14 @@ class Cambridge(WebService):
seg = self._get_field('pronunciation') seg = self._get_field('pronunciation')
return seg.get('BrE', u'') if seg else u'' 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): def _fld_mp3(self, fld):
audio_url = self._get_field('pronunciation')[fld] audio_url = self._get_field('pronunciation')[fld]
if cambridge_download_mp3 and audio_url: if cambridge_download_mp3 and audio_url:
@ -81,6 +96,14 @@ class Cambridge(WebService):
return self.get_anki_label(filename, 'audio') return self.get_anki_label(filename, 'audio')
return '' 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') @export('AME_PRON')
def fld_mp3_us(self): def fld_mp3_us(self):
return self._fld_mp3('AmEmp3') return self._fld_mp3('AmEmp3')
@ -88,7 +111,7 @@ class Cambridge(WebService):
@export('BRE_PRON') @export('BRE_PRON')
def fld_mp3_uk(self): def fld_mp3_uk(self):
return self._fld_mp3('BrEmp3') return self._fld_mp3('BrEmp3')
@export('DEF') @export('DEF')
def fld_definition(self): def fld_definition(self):
val = self._get_field('def') val = self._get_field('def')