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

Merge pull request #41 from patzzz/master

Browse Source 
Extract images and examples with audios from Longman (MDX-LDOCE6)
This commit is contained in:
sthoo 2018-08-20 23:45:44 +08:00 committed by GitHub
commit c1a007139e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 92 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
addons/fastwq/service/dict/LDOCE6.py
View File

@ -1,4 +1,5 @@
#-*- coding:utf-8 -*-
import os
import re
from ..base import *
@ -62,6 +63,24 @@ class Ldoce6(MdxService):
def fld_voiceame(self):
return self._fld_voice(self.get_html(), 'us')
def _fld_image(self, img):
val = '/' + img
# file extension isn't always jpg
file_extension = os.path.splitext(img)[1][1:].strip().lower()
name = get_hex_name('mdx-'+self.unique.lower(), val, file_extension)
name = self.save_file(val, name)
if name:
return self.get_anki_label(name, 'img')
return ''
@export('IMAGE')
def fld_image(self):
html = self.get_html()
m = re.search(r'<span class="imgholder"><img src="(.*?)".*?></span>', html)
if m:
return self._fld_image(m.groups()[0])
return ''
@export('EXAMPLE')
def fld_sentence(self):
m = re.findall(r'<span class="example"\s*.*>\s*.*<\/span>', self.get_html())
@ -73,12 +92,37 @@ class Ldoce6(MdxService):
for element in el_list]
my_str = ''
for i_str in maps:
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str)
i_str = i_str.replace('&nbsp;', '')
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str).strip()
my_str = my_str + '<li>' + i_str + '</li>'
return self._css(my_str)
return ''
def _fld_audio(self, audio):
name = get_hex_name('mdx-'+self.unique.lower(), audio, 'mp3')
name = self.save_file(audio, name)
if name:
return self.get_anki_label(name, 'audio')
return ''
@export(u'Examples with audios')
def fld_sentence_audio(self):
m = re.findall(r'<span class="example"\s*.*>\s*.*<\/span>', self.get_html())
if m:
soup = parse_html(m[0])
el_list = soup.findAll('span', {'class':'example'})
if el_list:
maps = [u''.join(str(content).decode('utf-8') for content in element.contents)
for element in el_list]
my_str = ''
for i_str in maps:
sound = re.search(r'<a[^>]+?href=\"sound\:\/(.*?\.mp3)\".*</a>', i_str)
if sound:
mp3 = self._fld_audio(sound.groups()[0])
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str).strip()
my_str = my_str + '<li>' + i_str + ' ' + mp3 + '</li>'
return self._css(my_str)
return ''
@export('DEF')
def fld_definate(self):
m = m = re.findall(r'<span class="def"\s*.*>\s*.*<\/span>', self.get_html())

48
addons21/fastwq/service/dict/LDOCE6.py
View File

@ -1,4 +1,5 @@
#-*- coding:utf-8 -*-
import os
import re
from ..base import *
@ -62,6 +63,24 @@ class Ldoce6(MdxService):
def fld_voiceame(self):
return self._fld_voice(self.get_html(), 'us')
def _fld_image(self, img):
val = '/' + img
# file extension isn't always jpg
file_extension = os.path.splitext(img)[1][1:].strip().lower()
name = get_hex_name('mdx-'+self.unique.lower(), val, file_extension)
name = self.save_file(val, name)
if name:
return self.get_anki_label(name, 'img')
return ''
@export('IMAGE')
def fld_image(self):
html = self.get_html()
m = re.search(r'<span class="imgholder"><img src="(.*?)".*?></span>', html)
if m:
return self._fld_image(m.groups()[0])
return ''
@export('EXAMPLE')
def fld_sentence(self):
m = re.findall(r'<span class="example"\s*.*>\s*.*<\/span>', self.get_html())
@ -73,12 +92,37 @@ class Ldoce6(MdxService):
for element in el_list]
my_str = ''
for i_str in maps:
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str)
i_str = i_str.replace('&nbsp;', '')
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str).strip()
my_str = my_str + '<li>' + i_str + '</li>'
return self._css(my_str)
return ''
def _fld_audio(self, audio):
name = get_hex_name('mdx-'+self.unique.lower(), audio, 'mp3')
name = self.save_file(audio, name)
if name:
return self.get_anki_label(name, 'audio')
return ''
@export(u'Examples with audios')
def fld_sentence_audio(self):
m = re.findall(r'<span class="example"\s*.*>\s*.*<\/span>', self.get_html())
if m:
soup = parse_html(m[0])
el_list = soup.findAll('span', {'class':'example'})
if el_list:
maps = [u''.join(str(content).decode('utf-8') for content in element.contents)
for element in el_list]
my_str = ''
for i_str in maps:
sound = re.search(r'<a[^>]+?href=\"sound\:\/(.*?\.mp3)\".*</a>', i_str)
if sound:
mp3 = self._fld_audio(sound.groups()[0])
i_str = re.sub(r'<a[^>]+?href=\"sound\:.*\.mp3\".*</a>', '', i_str).strip()
my_str = my_str + '<li>' + i_str + ' ' + mp3 + '</li>'
return self._css(my_str)
return ''
@export('DEF')
def fld_definate(self):
m = m = re.findall(r'<span class="def"\s*.*>\s*.*<\/span>', self.get_html())