04 Python正则表达式 爬虫程序 变量的引用，浅拷贝，深拷贝 多线程 进程锁 数据库模块

import re
In [40]: s=r"abc" 定义一个
In [42]:re.findall(s,"abcfdf")  在 "abcfdf" 里面查找abc
Out[42]: ['abc']

In [43]: s=r't[io]p'
In [44]: a='tip top hahanihao'
In [45]: re.findall(s,a)
Out[45]: ['tip', 'top']

In [66]: r1=r'abc'
In [67]:re.findall(r1,'d^abcf')
Out[67]: ['abc']
In [68]: r1=r'^abc'
In [69]:re.findall(r1,'d^abcf')
Out[69]: []

In [70]: r1=r'\^abc'
In [71]:re.findall(r1,'d^abcf')
Out[71]: ['^abc']

In [72]: r2=r'010-\d\d\d\d'
In [73]: s2='010-123'
In [74]: re.findall(r2,s2)
Out[74]: []     前面少一个 后面就匹配不到

In [75]: s2='010-1236'
In [76]: re.findall(r2,s2)
Out[76]: ['010-1236']

In [77]: r2=r'010-\d{4}' 重复出现的次数描述
In [78]: re.findall(r2,s2)
Out[78]: ['010-1236']

In [79]: r2=r'010-\d*'
In [81]: s2='010-12365345234'
In [82]: re.findall(r2,s2)
Out[82]: ['010-12365345234']

In [83]: r2=r'010-abc*'重复出现c，没有c也可以
In [84]: s2='010-abcc'
In [85]: re.findall(r2,s2)
Out[85]: ['010-abcc']
In [86]: s2='010-abcc23'
In [87]: re.findall(r2,s2)
Out[87]: ['010-abcc']

In [91]:r2=r"ab{8}"   只是匹配到有8次的
In [92]:r2=r"ab{2,9}"  匹配2到9次的
｛0，｝等同于*
｛1，｝等同于+
｛0，1｝  等同于？
｛0，2｝

In [94]:re.findall(r4,"0376-12345678")
Out[94]: ['0376-12345678']

In [95]:re.findall(r4,"037612345678")
Out[95]: ['037612345678']

In [93]:r4=r"\d{3,4}-?\d{8}"
In [96]: p_tel=re.compile(r4)  任何表达式都可以
In [98]: p_tel.findall('037612345678')  再来匹配
Out[98]: ['037612345678']

In [99]:r5=re.compile(r'welcome',re.I)
In [100]:r5.findall("WeLcoMe")
Out[100]: ['WeLcoMe']

In [105]:r5=re.compile(r'welcome',re.I)
In [106]: r5.match('welcomehaha')
Out[106]: <_sre.SRE_Matchat 0x7f7a67b2e5e0>  welcome在前面可以匹配到
In [107]: r5.match('hahwelcome haha') 不在前面就匹配不到

In [108]: r5.search('hahwelcome haha')
Out[108]: <_sre.SRE_Matchat 0x7f7a67b2e648>
In [109]: r5.search('welcomehaha')
Out[109]: <_sre.SRE_Matchat 0x7f7a67b2e440>
In [110]: r5.search('hahwelcome')
Out[110]: <_sre.SRE_Matchat 0x7f7a67b2e6b0>

In [1]: import re
In [2]: r1=r'qwe.com'
In [3]:re.findall(r1,"qwe.com")
Out[3]: ['qwe.com']

In [4]:re.findall(r1,"qwe5com")
Out[4]: ['qwe5com']

In [6]:re.findall(r1,"qwe\ncom")
Out[6]: []

In [7]:re.findall(r1,"qwe\ncom",re.S)
Out[7]: ['qwe\ncom']

In [8]: s='''             定义s
...: hello
...: haha
...: nihao
...: haha123
...: welcome
...: '''

s的储存方式
In [12]: s
Out[12]:'\nhello\nhaha\nnihao\nhaha123\nwelcome\n'

In [9]: r=r'^haha'

In [10]: re.findall(r,s)      默认匹配不出来
Out[10]: []

In [11]: re.findall(r,s,re.M)   这样就可以了
Out[11]: ['haha', 'haha']
当正则表达式是r2的这样的时候，默认匹配不到
In [13]: r2='''
....: \d{3,4}
....: -?
....: \d{8}
....: '''

n [16]: r2           r2的实际存储
Out[16]:'\n\\d{3,4}\n-?\n\\d{8}\n'
In [14]:

In [14]:re.findall(r2,"010-12345678")    默认匹配不到
Out[14]: []

In [15]: re.findall(r2,"010-12345678",re.X)  re.X 就好了
Out[15]: ['010-12345678']

In [17]:email=r'\w{3}@\w+(\.com|\.cn)'

In [18]:re.findall(email,"hhh@hello.com")
Out[18]: ['.com']

In [29]: s='''            定义字符串
....: fdsf hello scr=csvt yes  jdskd
....: mjhsjk src=123 yes jdsa
....: nscr=234 yes
....: nhello scr=python yes ksa
....: '''
In [31]: print s   先来看一看
fdsf hello scr=csvt yes  jdskd
mjhsjk src=123 yes jdsa
nscr=234 yes
nhello scr=python yes ksa

In [24]: r1=r"helloscr=.+ yes"   定义正则表达式

In [32]: re.findall(r1,s)        匹配效果
Out[32]: ['hello scr=csvtyes', 'hello scr=python yes']

vim img.py  我的小爬虫

#!/usr/local/python27
import re
import urllib
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return(html)
def getImg(html):
reg = r'src="(.*?\.jpg)" pic'  这个pic困惑我好久
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
x=0
for imgurl in imglist:
urllib.urlretrieve (imgurl,'%s.jpg' %x)
x+=1
html = getHtml("http://tieba.baidu.com/p/3054941358?pid=50862060666#50862060666")
getImg(html)
#print html

In [1]:a=[1,2,3,['a','b'],'hello']

In [2]: b=a

In [3]: id(a)
Out[3]: 140690669992272

In [4]: id(b)
Out[4]: 140690669992272

In [5]: import copy

In [6]: c=copy.copy(a)

In [7]: id(c)
Out[7]: 140690670078720

In [9]: a[3].append('c')

In [10]: a
Out[10]: [1, 2, 3, ['a', 'b','c'], 'hello']

In [11]: c
Out[11]: [1, 2, 3, ['a', 'b','c'], 'hello']

In [12]: d=copy.deepcopy(a)

In [13]: id(a)
Out[13]: 140690669992272

In [14]: id(d)
Out[14]: 140690670200736         不一样

In [15]: a[3].append('f')

In [16]: a
Out[16]: [1, 2, 3, ['a', 'b','c', 'f'], 'hello']    不一样

In [17]: d
Out[17]: [1, 2, 3, ['a', 'b','c'], 'hello']

In [22]: id(a[3])
Out[22]: 140690669992416    不一样

In [23]: id(d[3])
Out[23]: 140690672885704

In [27]: import time

In [28]: for i in range(5):
print i
time.sleep(1)
....:
0
1
2
3
4

#!/usr/local/python27

import time
import thread

def t(x,y):
for i in range(y):
print x,i,"\n"
time.sleep(1)

thread.start_new_thread(t,(990487026,10))
thread.start_new_thread(t,(123456789,10))

time.sleep(10) 要大于线程生命周期

[root@localhost python]#python27 thred.py
123456789 0

990487026 0

123456789 1

990487026 1

123456789 2

990487026 2

990487026 3

#!/usr/local/python27
import time
import thread

def t(x,y,l):
for i in range(y):
print x,i,"\n"
time.sleep(1)
l.release()    执行完毕，释放锁

lock = thread.allocate_lock()生成一个锁
lock.acquire()                把锁锁上

thread.start_new_thread(t,(990487026,10,lock)) 把锁传进去

while lock.locked():          直到锁释放才结束进程
pass

yum install MySQL-python
yum install python-devel
yum install mysql-server
yum install python-setuptools
>>> import MySQLdb 载入模块
service mysqld start 启动
>>> conn = MySQLdb.connect(user='root',passwd='',host='127.0.0.1')保存连接状态
>>> conn =MySQLdb.connect() 或者是这个，默认mysql
>>> cur =conn.cursor() 用conn对象保存游标
>>>conn.select_db('test')  选择默认的user这个库