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

fix #79

Browse Source
This commit is contained in:
St.Huang 2018-10-28 11:44:46 +08:00
parent bd6c0b3d2d
commit 13bf8f6c30
2 changed files with 98 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
addons/fastwq/service/dict/cambridge.py
View File

@ -22,47 +22,55 @@ class Cambridge(WebService):
'def': '' 'def': ''
} }
#页 #english
element = soup.find('div', class_='entry-body__el clrd js-share-holder') element = soup.find('div', class_='link')
if element: if element:
#音 #页
header = element.find('div', class_='pos-header') elements = element.find_all('div', class_='entry-body__el clrd js-share-holder')
if header: header_found = False
tags = header.find_all('span', class_='pron-info') for element in elements:
if tags: if element:
for tag in tags: #音
r = tag.find('span', class_='region') if not header_found:
reg = str(r.get_text()).decode('utf-8') if r else u'' header = element.find('div', class_='pos-header')
pn = 'AmE' if reg=='us' else 'BrE' if header:
p = tag.find('span', class_='pron') tags = header.find_all('span', class_='pron-info')
result['pronunciation'][pn] = str(p.get_text()).decode('utf-8') if p else u'' if tags:
snd = tag.find('span', class_='circle circle-btn sound audio_play_button') for tag in tags:
if snd: r = tag.find('span', class_='region')
result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3') reg = str(r.get_text()).decode('utf-8') if r else u''
#义 pn = 'AmE' if reg=='us' else 'BrE'
body = element.find('div', class_='pos-body') p = tag.find('span', class_='pron')
if body: result['pronunciation'][pn] = str(p.get_text()).decode('utf-8') if p else u''
tags = body.find_all('div', class_='def-block pad-indent') snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
if tags: if snd:
l = [] result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3')
for tag in tags: header_found = True
i = tag.find('span', class_='def-info') #义
d = tag.find('b', class_='def') body = element.find('div', class_='pos-body')
e = tag.find('div', class_='examp emphasized') if body:
l.append( tags = body.find_all('div', class_='def-block pad-indent')
u'<li><span class="epp-xref">{0}</span>\ if tags:
<b class="def">{1}</b>\ l = result['def_list']
<div class="examp">{2}</div></li>'.format( for tag in tags:
str(i.get_text()).decode('utf-8') if i else u'', i = tag.find('span', class_='def-info')
str(d.get_text()).decode('utf-8') if d else u'', d = tag.find('b', class_='def')
str(e.get_text()).decode('utf-8') if e else u'' es = tag.find_all('div', class_='examp emphasized')
) l.append(
) u'<li>{0}{1}{2}</li>'.format(
result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>' u'<span class="epp-xref">{0}</span>'.format(str(i.get_text()).decode('utf-8')) if i else u'',
img = body.find('img', class_='lightboxLink') u'<b class="def">{0}</b>'.format(str(d.get_text()).decode('utf-8')) if d else u'',
if img: u''.join(
result['image'] = cambridge_url_base + img.get('data-image') u'<div class="examp">{0}</div>'.format(str(e.get_text()).decode('utf-8')) if e else u''
result['thumb'] = cambridge_url_base + img.get('src') for e in es
)
)
)
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)

91
addons21/fastwq/service/dict/cambridge.py
View File

@ -19,50 +19,59 @@ class Cambridge(WebService):
'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''}, 'pronunciation': {'AmE': '', 'BrE': '', 'AmEmp3': '', 'BrEmp3': ''},
'image': '', 'image': '',
'thumb': '', 'thumb': '',
'def': '' 'def': '',
'def_list': []
} }
#页 #english
element = soup.find('div', class_='entry-body__el clrd js-share-holder') element = soup.find('div', class_='link')
if element: if element:
#音 #页
header = element.find('div', class_='pos-header') elements = element.find_all('div', class_='entry-body__el clrd js-share-holder')
if header: header_found = False
tags = header.find_all('span', class_='pron-info') for element in elements:
if tags: if element:
for tag in tags: #音
r = tag.find('span', class_='region') if not header_found:
reg = r.get_text() if r else u'' header = element.find('div', class_='pos-header')
pn = 'AmE' if reg=='us' else 'BrE' if header:
p = tag.find('span', class_='pron') tags = header.find_all('span', class_='pron-info')
result['pronunciation'][pn] = p.get_text() if p else u'' if tags:
snd = tag.find('span', class_='circle circle-btn sound audio_play_button') for tag in tags:
if snd: r = tag.find('span', class_='region')
result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3') reg = r.get_text() if r else u''
#义 pn = 'AmE' if reg=='us' else 'BrE'
body = element.find('div', class_='pos-body') p = tag.find('span', class_='pron')
if body: result['pronunciation'][pn] = p.get_text() if p else u''
tags = body.find_all('div', class_='def-block pad-indent') snd = tag.find('span', class_='circle circle-btn sound audio_play_button')
if tags: if snd:
l = [] result['pronunciation'][pn+'mp3'] = cambridge_url_base + snd.get('data-src-mp3')
for tag in tags: header_found = True
i = tag.find('span', class_='def-info') #义
d = tag.find('b', class_='def') body = element.find('div', class_='pos-body')
e = tag.find('div', class_='examp emphasized') if body:
l.append( tags = body.find_all('div', class_='def-block pad-indent')
u'<li><span class="epp-xref">{0}</span>\ if tags:
<b class="def">{1}</b>\ l = result['def_list']
<div class="examp">{2}</div></li>'.format( for tag in tags:
i.get_text() if i else u'', i = tag.find('span', class_='def-info')
d.get_text() if d else u'', d = tag.find('b', class_='def')
e.get_text() if e else u'' es = tag.find_all('div', class_='examp emphasized')
) l.append(
) u'<li>{0}{1}{2}</li>'.format(
result['def'] = u'<ul>' + u''.join(s for s in l) + u'</ul>' u'<span class="epp-xref">{0}</span>'.format(i.get_text()) if i else u'',
img = body.find('img', class_='lightboxLink') u'<b class="def">{0}</b>'.format(d.get_text()) if d else u'',
if img: u''.join(
result['image'] = cambridge_url_base + img.get('data-image') u'<div class="examp">{0}</div>'.format(e.get_text()) if e else u''
result['thumb'] = cambridge_url_base + img.get('src') for e in es
)
)
)
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)