def init_list():
from models import XmlItem
temp = []
try:
f = open(xmlpath, 'r')
xml = f.read()
except Exception:
xml = ''
finally:
try:
f.close()
except Exception:
pass
if not xml:
return temp
xxs = Selector(text=xml)
items = xxs.xpath('//wordbook/item')
for item in items:
name = item.xpath('./name/text()').extract()[0]
one = XmlItem(name)
create_time = item.xpath('./create_time/text()').extract()[0]
create_time = datetime.strptime(create_time, '%Y-%m-%d %H:%M:%S')
access_time = item.xpath('./access_time/text()').extract()[0]
access_time = datetime.strptime(access_time, '%Y-%m-%d %H:%M:%S')
score = item.xpath('./score/text()').extract()[0]
score = int(score)
setattr(one, 'create_time', create_time)
setattr(one, 'access_time', access_time)
setattr(one, 'score', score)
temp.append(one)
return temp
def init_list():
from models import XmlItem
temp = []
try:
f = open(xmlpath, 'r')
xml = f.read()
except:
xml = ''
finally:
try:
f.close()
except:
pass
if not xml:
return temp
xxs = Selector(text=xml)
items = xxs.xpath('//wordbook/item')
for item in items:
name = item.xpath('./name/text()').extract()[0]
one = XmlItem(name)
create_time = item.xpath('./create_time/text()').extract()[0]
create_time = datetime.strptime(create_time, '%Y-%m-%d %H:%M:%S')
access_time = item.xpath('./access_time/text()').extract()[0]
access_time = datetime.strptime(access_time, '%Y-%m-%d %H:%M:%S')
score = item.xpath('./score/text()').extract()[0]
score = int(score)
setattr(one, 'create_time', create_time)
setattr(one, 'access_time', access_time)
setattr(one, 'score', score)
temp.append(one)
return temp
def query(self, word):
url = "http://dict.youdao.com/search?tab=chn&keyfrom=dict.top&q="
url += word
before_fetching = datetime.now()
html = self.get_html(url)
if not html:
return ''
after_fetching = datetime.now()
time_fetching = after_fetching - before_fetching
print
print word
print datetime.strftime(before_fetching, '%Y/%m/%d %H:%M:%S')
print 'time_fetching %.2f' % time_fetching.total_seconds()
hxs = Selector(text=html)
phonetics = hxs.xpath('//div[@id="phrsListTab"]/h2[1]/div[1]/span')
phonetic = ''
for ph in phonetics:
ph = ph.xpath('./span/text()').extract()
if len(ph) > 0:
phonetic += ph[0]
lis = hxs.xpath(
'//div[@id="phrsListTab"]/div[@class="trans-container"]/ul/li')
meaning = ''
for li in lis:
try:
temp_meaning = li.xpath('./text()').extract()[0] + '\n'
except:
temp_meaning = ''
if word.capitalize() in temp_meaning and u'人名' in temp_meaning:
continue
else:
meaning += temp_meaning
examples = hxs.xpath('//div[@id="bilingual"]/ul/li')
example = ''
for li in examples:
example_en = li.xpath('./p[1]/span//text()').extract()
example_cn = li.xpath('./p[2]/span//text()').extract()
example += ''.join(example_en) + '\n'
example += ''.join(example_cn) + '\n'
if not meaning:
print 'wrong word ?'
try:
possible = hxs.xpath(
'//div[@class="error-typo"]/h4/text()'
).extract()[0].strip() + '\n'
possible += hxs.xpath(
'//div[@class="error-typo"]//a/text()').extract()[0]
except:
possible = ''
return possible
item_dict = {}
item_dict['name'] = word
item_dict['phonetic'] = phonetic.encode('utf8')
item_dict['meaning'] = meaning.encode('utf8')
item_dict['example'] = example.encode('utf8')
return item_dict
def query(self):
before_fetching = datetime.now()
html = self.get_html(get_url(self.word.value))
if not html:
return ''
after_fetching = datetime.now()
time_fetching = after_fetching - before_fetching
print()
print(self.word.value)
print(datetime.strftime(before_fetching, '%Y/%m/%d %H:%M:%S'))
try:
print('time_fetching %.2f' % time_fetching.total_seconds())
except Exception:
print('time_fetching %.2f' % time_fetching.seconds)
hxs = Selector(text=html)
if self.word.lang == 'cn':
return self.query_cn(hxs)
else:
return self.query_en(hxs)
def query(self, word):
url = "http://dict.youdao.com/search?tab=chn&keyfrom=dict.top&q="
url += word
before_fetching = datetime.now()
html = self.get_html(url)
if not html:
return ''
after_fetching = datetime.now()
time_fetching = after_fetching - before_fetching
print
print word
print datetime.strftime(before_fetching, '%Y/%m/%d %H:%M:%S')
try:
print 'time_fetching %.2f' % time_fetching.total_seconds()
except:
print 'time_fetching %.2f' % time_fetching.seconds
hxs = Selector(text=html)
phonetics = hxs.xpath('//div[@id="phrsListTab"]/h2[1]/div[1]/span')
phonetic = ''
for ph in phonetics:
ph = ph.xpath('./span/text()').extract()
if len(ph) > 0:
phonetic += ph[0]
lis = hxs.xpath(
'//div[@id="phrsListTab"]/div[@class="trans-container"]/ul/li')
meaning = ''
for li in lis:
try:
temp_meaning = li.xpath('./text()').extract()[0] + '\n'
except:
temp_meaning = ''
if word.capitalize() in temp_meaning and u'人名' in temp_meaning:
continue
else:
meaning += temp_meaning
examples = hxs.xpath('//div[@id="bilingual"]/ul/li')
example = ''
for li in examples:
example_en = li.xpath('./p[1]/span//text()').extract()
example_cn = li.xpath('./p[2]/span//text()').extract()
example += ''.join(example_en) + '\n'
example += ''.join(example_cn) + '\n'
if not meaning:
print 'wrong word ?'
try:
possible = hxs.xpath(
'//div[@class="error-typo"]/h4/text()'
).extract()[0].strip() + '\n'
possible += hxs.xpath(
'//div[@class="error-typo"]//a/text()').extract()[0]
except:
possible = ''
return possible
item_dict = {}
item_dict['name'] = word
item_dict['phonetic'] = phonetic.encode('utf8')
item_dict['meaning'] = meaning.encode('utf8')
item_dict['example'] = example.encode('utf8')
return item_dict