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

Merge pull request #132 from JavanZhu/master

Browse Source 
Fix bug that can not query phrasal verbs like 'turn out', 'allude to'...
This commit is contained in:
sthoo 2019-03-21 22:45:03 +08:00 committed by GitHub
commit 461986b003
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 32 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
addons21/fastwq/service/dict/cambridge.py
View File

@ -8,6 +8,7 @@ cambridge_url_base = u'https://dictionary.cambridge.org/'
cambridge_download_mp3 = True cambridge_download_mp3 = True
cambridge_download_img = True cambridge_download_img = True
class Cambridge(WebService): class Cambridge(WebService):
def __init__(self): def __init__(self):
@ -27,15 +28,15 @@ class Cambridge(WebService):
'def_list': [] 'def_list': []
} }
#english # english
element = soup.find('div', class_='di-body') element = soup.find('div', class_='di-body')
if element: if element:
#页 # 页
elements = element.find_all('div', class_='entry-body__el clrd js-share-holder') elements = element.find_all('div', class_='entry-body__el clrd js-share-holder')
header_found = False header_found = False
for element in elements: for element in elements:
if element: if element:
#音 # 音
if not header_found: if not header_found:
header = element.find('div', class_='pos-header') header = element.find('div', class_='pos-header')
if header: if header:
@ -54,35 +55,37 @@ class Cambridge(WebService):
# 词性 # 词性
pg = element.find('span', class_='posgram ico-bg') pg = element.find('span', class_='posgram ico-bg')
#义 # 义
body = element.find('div', class_='pos-body') senses = element.find_all('div', class_='sense-block')
if body: if senses:
tags = body.find_all('div', class_='def-block pad-indent') for sense in senses:
if tags: dbs = sense.find_all('div', class_='def-block pad-indent')
l = result['def_list'] if dbs:
for tag in tags: l = result['def_list']
i = tag.find('span', class_='def-info') for db in dbs:
d = tag.find('b', class_='def') i = sense.find('span', class_='def-info')
trans = tag.find('span', class_='trans') d = db.find('b', class_='def')
es = tag.find_all('div', class_='examp emphasized') tran = db.find('span', class_='trans')
l.append( examps = db.find_all('div', class_='examp emphasized')
u'<li>{0}{1}{2} {3}{4}</li>'.format( l.append(
'<span class="epp-xref">{0}</span>'.format(pg.get_text() if pg else ''), u'<li>{0}{1}{2} {3}{4}</li>'.format(
u'<span class="epp-xref">{0}</span>'.format(i.get_text()) if i else u'', '<span class="epp-xref">{0}</span>'.format(pg.get_text() if pg else ''),
u'<b class="def">{0}</b>'.format(d.get_text()) if d else u'',
u'<span class="trans">{0}</span>'.format(trans.get_text()) if trans else u'', u'<span class="epp-xref">{0}</span>'.format(i.get_text()) if i else u'',
u''.join( u'<b class="def">{0}</b>'.format(d.get_text()) if d else u'',
u'<div class="examp">{0}</div>'.format(e.get_text()) if e else u''
for e in es u'<span class="trans">{0}</span>'.format(tran.get_text()) if tran else u'',
u''.join(
u'<div class="examp">{0}</div>'.format(e.get_text()) if e else u''
for e in examps
)
) )
) )
) 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 = sense.find('img', class_='lightboxLink')
img = body.find('img', class_='lightboxLink') if img:
if img: result['image'] = cambridge_url_base + img.get('data-image')
result['image'] = cambridge_url_base + img.get('data-image') result['thumb'] = cambridge_url_base + img.get('src')
result['thumb'] = cambridge_url_base + img.get('src')
return self.cache_this(result) return self.cache_this(result)