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

Merge pull request #141 from JavanZhu/master

Browse Source 
Fix bug
This commit is contained in:
sthoo 2019-04-14 14:57:00 +08:00 committed by GitHub
commit 24169ae90b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
addons21/fastwq/service/dict/cambridge.py
View File

@ -31,7 +31,7 @@ class Cambridge(WebService):
} }
# english # english
element = soup.find('div', class_='di-body') element = soup.find('div', class_='cdo-dblclick-area')
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')
@ -56,18 +56,11 @@ class Cambridge(WebService):
header_found = True header_found = True
# 义 # 义
if 'english-chinese-simplified' in self._get_url(): senses = element.find_all('div', id=re.compile("english-chinese-simplified*|"
senses = element.find_all('div', id=re.compile("english-chinese-simplified*")) "english-chinese-traditional*|"
elif 'english-chinese-traditional' in self._get_url(): "cald4*|"
senses = element.find_all('div', id=re.compile("english-chinese-traditional*")) "cbed*|"
else: "cacd*"))
senses = element.find_all('div', id=re.compile("cald4*"))
# proficiency之类的词语
if not senses:
senses = element.find_all('div', id=re.compile("cbed*"))
# shoplift之类的词语
if not senses:
senses = element.find_all('div', id=re.compile("cacd*"))
# 词性 # 词性
span_posgram = element.find('span', class_='posgram ico-bg') span_posgram = element.find('span', class_='posgram ico-bg')
pos_gram = (span_posgram.get_text() if span_posgram else '') pos_gram = (span_posgram.get_text() if span_posgram else '')
@ -88,22 +81,25 @@ class Cambridge(WebService):
if sense_body: if sense_body:
l = result['def_list'] l = result['def_list']
for block in sense_body:
if isinstance(block, Tag) is not True:
continue
phrase = None def extract_sense(block, phrase=None):
if isinstance(block, Tag) is not True:
return
block_type = block['class'][0] block_type = block['class'][0]
if block_type == 'def-block': if block_type == 'def-block':
pass pass
elif block_type == 'phrase-block': elif block_type == 'phrase-block':
phrase_header = block.find('span', class_='phrase-head') _phrase_header = block.find('span', class_='phrase-head')
phrase = phrase_header.get_text() if phrase_header else None _phrase_body = block.find('div', class_='phrase-body pad-indent')
pass if _phrase_body:
for p_b in _phrase_body:
extract_sense(p_b, _phrase_header.get_text() if _phrase_header else None)
return
elif block_type == 'runon-body': elif block_type == 'runon-body':
pass pass
else: else:
continue return
span_df = block.find('span', class_='def-info') span_df = block.find('span', class_='def-info')
def_info = (span_df.get_text().replace('›', '') if span_df else '') def_info = (span_df.get_text().replace('›', '') if span_df else '')
@ -125,6 +121,9 @@ class Cambridge(WebService):
) )
) )
) )
for b in sense_body:
extract_sense(b)
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 = sense.find('img', class_='lightboxLink')
if img: if img: