def district_path():
translater = pinyin.PinYin()
# db = MySQLdb.connect('rds7di028yhg19m2v656o.mysql.rds.aliyuncs.com',"alphago","Alphago0311",'realestate' ,charset="utf8")
db = MySQLdb.connect('127.0.0.1',"root","root",'realestate' ,charset="utf8")
cr = db.cursor(cursorclass = MySQLdb.cursors.DictCursor)
sql = 'alter table district add path varchar(64) after name'
cr.execute(sql)
db.commit()
sql = 'select * from district'
cr.execute(sql)
districts = cr.fetchall()
for d in districts:
sql = 'update district set path = "'+ str(translater.convert(string=d['name'],join=True)) + '" where id = '+ str(d['id'])
cr.execute(sql)
print sql
db.commit()
db.close()
return True
#- coding: utf-8 -*-.
import urllib2
import re
import pinyin
import codecs
response = urllib2.urlopen(u"http://quote.eastmoney.com/stocklist.html")
content = response.read()
content = content.strip()
pattern = re.compile(
r'<li><a target="_blank" href="http://quote.eastmoney.com/(?P<code>\w*).html">(?P<name>.*)\(.*\)</a></li>'
)
result = u""
pinyin = pinyin.PinYin()
for m in re.finditer(pattern, content):
code = m.groups()[0][2:].decode(u'gb2312')
name = m.groups()[1]
if not isinstance(name, unicode):
try:
name = name.decode(u'gb2312')
except:
name = name.decode(u'gbk')
if u'退市' in name:
continue
main_type = u'未知'
submain_type1 = u''
submain_type2 = u''
abbr = pinyin.hanzi2pinyin_split(string=name, split=u"", firstcode=True)
else ''
end as PARENTID ,
'GS' as ORGTYPE,
a.create_time,
case when LENGTH(a.path)=8 then (SELECT id from org_unit where path='00000001')
when LENGTH(a.path)=12 then (SELECT CONCAT(a.id,',',b.id) from org_unit b where LENGTH(b.path)=8 and SUBSTR(a.path ,1 ,8)=b.path)
when LENGTH(a.path)=16 then (SELECT CONCAT('670869647114347',',',a.id,',',b.id)from org_unit b where LENGTH(b.path)=12 and SUBSTR(a.path ,1 ,12)=b.path)
when LENGTH(a.path)=20 then (SELECT CONCAT(a.id,',',b.id)from org_unit b where LENGTH(b.path)=16 and SUBSTR(a.path ,1 ,16)=b.path)
when LENGTH(a.path)=24 then (SELECT CONCAT(a.id,',',b.id)from org_unit b where LENGTH(b.path)=20 and SUBSTR(a.path ,1 ,20)=b.path)
else ''
end as PARENTIDS,a.ORG_ACCOUNT_ID
from org_unit a) m) d on d.ID=a.ORG_DEPARTMENT_ID and d.ORG_ACCOUNT_ID=a.ORG_ACCOUNT_ID'''
# 字段为中文转换拼音实例
List_ID = []
py = pinyin.PinYin()
py.load_word()
# 使用execute方法执行SQL语句
try:
# cursor.execute(del_sql_unit)
# cursor.execute(del_sql_umuser)
cursor.execute(sql_unit)
cursor.execute(sql_memer)
cursor.execute(tmp_loginid)
loginid_sql = cursor.fetchall()
loginid_row = cursor.rowcount
for i in range(loginid_row):
# loginid_sql[i][1] = py.hanzi2pinyin_split(string=loginid_sql[i][0], split="-").replace('-', '')
# print loginid_sql[i][1]
sql_pinyin = "update tmp_umuser set logonid = '%s' where username = '******'" \
#!/usr/bin/env python
import pinyin
test = pinyin.PinYin()
test.load_word()
def getpinyin(s):
s2 = ''
try:
s = s.decode('utf8')
except:
pass
for i in s:
try:
si = test.hanzi2pinyin(string=i)[0]
if si == '':
si = i
except:
si = i
s2 += si
return s2.encode('utf8')
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
from pybtex.style.sorting import BaseSortingStyle
import pinyin
import re
import os, sys
wordfile = re.sub(r"[^/\\]*$", "word.data", __file__)
if not os.path.exists(wordfile):
wordfile = re.sub(r"[^/\\]*$", "word.data", os.path.abspath(sys.argv[0]))
if not os.path.exists(wordfile):
wordfile = "word.data"
#print "Data File: " + os.path.abspath(wordfile)
pymod = pinyin.PinYin(wordfile)
pymod.load_word()
class SortingStyle(BaseSortingStyle):
name = 'chinese_author'
def sorting_key(self, entry):
if entry.type in ('book', 'inbook'):
author_key = self.author_editor_key(entry)
else:
author_key = self.persons_key(entry.persons['author'])
return (author_key, entry.fields.get('year', ''),
entry.fields.get('title', ''))
def persons_key(self, persons):
import codecs
from ..trie import Trie
import zh
import pinyin
stop_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'stopwords.txt')
pinyin_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'pinyin.txt')
stop = set()
fr = codecs.open(stop_path, 'r', 'utf-8')
for word in fr:
stop.add(word.strip())
fr.close()
pin = pinyin.PinYin(pinyin_path)
re_zh = re.compile('([\u4E00-\u9FA5]+)')
def filter_stop(words):
return list(filter(lambda x: x not in stop, words))
def zh2hans(sent):
return zh.transfer(sent)
def get_sentences(doc):
line_break = re.compile('[\r\n]')
delimiter = re.compile('[，。？！；]')
sentences = []