#判断表存不存在来创建表

def create_table():



    conn = sqlite3.connect(db_name)

    try:

        create_tb_cmd='''

        CREATE TABLE IF NOT EXISTS USER

        (NAME TEXT,

        AGE INT,

        SALARY REAL);

        '''

        #主要就是上面的语句

        conn.execute(create_tb_cmd)

    except:

        print "Create table failed"

        return False

    insert_dt_cmd='''

    INSERT INTO USER (NAME,AGE,SALARY) VALUES ("Rocky",10,20.1);

    '''

    conn.execute(insert_dt_cmd)

    conn.commit()

    conn.close()

class C:

    @classmethod

    def f(cls, arg1, arg2, ...): ...

class Data_test(object):

    day=0

    month=0

    year=0

    def __init__(self,year=0,month=0,day=0):

        self.day=day

        self.month=month

        self.year=year



    def out_date(self):

        print "year :"

        print self.year

        print "month :"

        print self.month

        print "day :"

        print self.day

t=Data_test(2016,8,1)

t.out_date()

year :

2016

month :

8

day :

1

string_date='2016-8-1'

year,month,day=map(int,string_date.split('-'))

s=Data_test(year,month,day)

class Data_test2(object):

    day=0

    month=0

    year=0

    def __init__(self,year=0,month=0,day=0):

        self.day=day

        self.month=month

        self.year=year



    @classmethod

    def get_date(cls,

string_date):

        #这里第一个参数是cls， 表示调用当前的类名

        year,month,day=map(int,string_date.split('-'))

        date1=cls(year,month,day)

        #返回的是一个初始化后的类

        return date1



    def out_date(self):

        print "year :"

        print self.year

        print "month :"

        print self.month

        print "day :"

        print self.day

r=Data_test2.get_date("2016-8-6")

r.out_date()

year :

2016

month :

8

day :

1

    if df is None:

        print "None len==0"

        return False

__author__ = 'rocky'

import urllib,urllib2,StringIO,gzip

url="http://image.xitek.com/photo/2 ... ot%3B

filname=url.split("/")[-1]

req=urllib2.Request(url)

resp=urllib2.urlopen(req)

content=resp.read()

#data = StringIO.StringIO(content)

#gzipper = gzip.GzipFile(fileobj=data)

#html = gzipper.read()

f=open(filname,'w')

f.write()

f.close()

Don't use BeautifulSoup, use lxml.soupparser then you're sitting on top of the power of lxml and can use the good bits of BeautifulSoup which is to deal with really broken and crappy HTML.
 
 
 
9down vote
In summary, 

lxml

 is positioned as a lightning-fast production-quality html and xml parser that, by the way, also includes a 

soupparser

 module to fall back on BeautifulSoup's functionality. 

BeautifulSoup

is a one-person project, designed to save you time to quickly extract data out of poorly-formed html or xml.
lxml documentation says that both parsers have advantages and disadvantages. For this reason, 

lxml

 provides a 

soupparser

 so you can switch back and forth. Quoting,
[quote]
BeautifulSoup uses a different parsing approach. It is not a real HTML parser but uses regular expressions to dive through tag soup. It is therefore more forgiving in some cases and less good in others. It is not uncommon that lxml/libxml2 parses and fixes broken HTML better, but BeautifulSoup has superiour support for encoding detection. It very much depends on the input which parser works better.

The downside of using this parser is that it is much slower than the HTML parser of lxml. So if performance matters, you might want to consider using soupparser only as a fallback for certain cases.

lxml

BeautifulSoup

soupparser

lxml

BeautifulSoup

lxml

[code]>>> from BeautifulSoup import UnicodeDammit



>>> def decode_html(html_string):

...     converted = UnicodeDammit(html_string, isHTML=True)

...     if not converted.unicode:

...         raise UnicodeDecodeError(

...             "Failed to detect encoding, tried [%s]",

...             ', '.join(converted.triedEncodings))

...     # print converted.originalEncoding

...     return converted.unicode



>>> root = lxml.html.fromstring(decode_html(tag_soup))

BeautifulSoup

That's it! Have fun! I wrote Beautiful Soup to save everybody time. Once you get used to it, you should be able to wrangle data out of poorly-designed websites in just a few minutes. Send me email if you have any comments, run into problems, or want me to know about your project that uses Beautiful Soup.

[code] --Leonard

[/code]

lxml has been downloaded from the Python Package Index more than two million times and is also available directly in many package distributions, e.g. for Linux or MacOS-X.

The C libraries libxml2 and libxslt have huge benefits:... Standards-compliant... Full-featured... fast. fast! FAST! ... lxml is a new Python binding for libxml2 and libxslt...

    list=[1,2,3,5,4,6,434,2323,333,99999]

    print "max of list is ",

    print max(list)

#-*-coding=utf-8-*-

__author__ = 'rocchen'

from lxml import html

from lxml import etree

import urllib2



def lxml_test():

    url="http://www.caixunzz.com"

    req=urllib2.Request(url=url)

    resp=urllib2.urlopen(req)

    #print resp.read()



    tree=etree.HTML(resp.read())

    href=tree.xpath('//a[@class="label"]/@href')

    #print href.tag

    for i in href:

        #print html.tostring(i)

        #print type(i)

        print i



    print type(href)



lxml_test()

>>> x = { }

>>> y = x

>>> x = { 'a' : 'b' }

>>> y

>>> { }

>>> x = { }

>>> y = x

>>> x['a'] = 'b'

>>> y

>>> { 'a' : 'b' }

p = subprocess.Popen(cmd, stdout = subprocess.PIPE, stdin = subprocess.PIPE, shell = True)

p.wait()

// hang here

print "finished"

p = subprocess.Popen(cmd, stdout = subprocess.PIPE, stdin = subprocess.PIPE, shell = True)

stdout, stderr = p.communicate()

p.wait()

print "Finsih"