常用模块 (二)

import pickle
class Cat:
 def __init__(self, name, age):
 self.name = name
 self.age = age
 def catchMouse(self):
 print(self.name, "抓??")
c = Cat("jerry", 18)
bs = pickle.dumps(c) # 序列化?个对象.
print(bs) # ?堆?进制. 看不懂
cc = pickle.loads(bs) # 把?进制反序列化成我们的对象
cc.catchMouse() # 猫依然是猫. 还可以抓??

# f = open("cat", mode="wb")
# pickle.dump(c, f) # 写?到?件中
# f.close()
f = open("cat", mode="rb")
cc = pickle.load(f) # 从?件中读取对象
cc.catchMouse()

lst = [Cat("jerry", 19), Cat("tommy", 20), Cat("alpha", 21)]
f = open("cat", mode="wb")
for el in lst:
 pickle.dump(el, f) # 写?到?件中
f.close()
f = open("cat", mode="rb")
for i in range(len(lst)):
 cc = pickle.load(f) # 从?件中读取对象
 cc.catchMouse()

import shelve
shelf = shelve.open("sylar")
# shelf["jay"] = "周杰伦"
print(shelf[‘jay‘])
shelf.close()

s = shelve.open("sylar")
# s["jay"] = {"name":"周杰伦", "age":18, "hobby":"哄?孩"}
print(s[‘jay‘])
s.close()

s = shelve.open("sylar")
s[‘jay‘][‘name‘] = "胡辣汤" # 尝试改变字典中的数据
s.close()
s = shelve.open("sylar")
print(s[‘jay‘]) # 并没有改变
s.close()

s = shelve.open("sylar", writeback=True)
s[‘jay‘][‘name‘] = "胡辣汤" # 尝试改变字典中的数据
s.close()
s = shelve.open("sylar")
print(s[‘jay‘]) # 改变了.
s.close()

s = shelve.open("sylar", writeback=True)
del s[‘jay‘]
s.close()
s = shelve.open("sylar")
print(s[‘jay‘]) # 报错了, 没有了
s.close()
s = shelve.open("sylar", writeback=True)
s[‘jay‘] = "周杰伦"
s[‘wlj‘] = "王?宏"
s.close()
s = shelve.open("sylar")
for k in s: # 像字典?样遍历
 print(k)
print(s.keys()) # 拿到所有key的集合
for k in s.keys():
 print(k)

for k, v in s.items(): # 像字典?样操作
print(k, v)
s.close()

wf = {
 "name":"汪峰",
 "age":18,
 "hobby":"上头条",
 "wife":{
 "name":‘?怡‘,
 "age":19,
 "hobby":["唱歌", "跳舞", "演戏"]
 }
}

<?xml version="1.0" encoding="utf-8" ?>
<wf>
 <name>汪峰</name>
 <age>18</age>
 <hobby>上头条</hobby>
 <wife>
 <name>?怡</name>
 <age>18</age>
 <hobbies>
 <hobby>唱歌</hobby>
 <hobby>跳舞</hobby>
 <hobby>演戏</hobby>
 </hobbies>
 </wife>
 
</wf>

import json
dic = {"a": "?王", "b": "萝莉", "c": "?清新"}
s = json.dumps(dic) # 把字典转化成json字符串
print(s) # {"a": "\u5973\u738b", "b": "\u841d\u8389", "c":
"\u5c0f\u6e05\u65b0"}
 

import json
dic = {"a": "?王", "b": "萝莉", "c": "?清新"}
s = json.dumps(dic, ensure_ascii=False) # 把字典转化成json字符串
print(s) # {"a": "?王", "b": "萝莉", "c": "?清新"}

import json
s = ‘{"a": "?王", "b": "萝莉", "c": "?清新"}‘
dic = json.loads(s)
print(type(dic), dic)

dic = {"a": "?王", "b": "萝莉", "c": "?清新"}
f = open("test.json", mode="w", encoding="utf-8")
json.dump(dic, f, ensure_ascii=False) # 把对象打散成json写?到?件中
f.close()

f = open("test.json", mode="r", encoding="utf-8")
dic = json.load(f)
f.close()
print(dic)

import json
lst = [{"a": 1}, {"b": 2}, {"c": 3}]
f = open("test.json", mode="w", encoding="utf-8")
for el in lst:
 json.dump(el, f)
f.close()

{‘a‘:1}{‘b‘:2}{‘c‘:3}

import json
lst = [{"a": 1}, {"b": 2}, {"c": 3}]
# 写?
f = open("test.json", mode="w", encoding="utf-8")
for el in lst:
 s = json.dumps(el, ensure_ascii=True) + "\n"
 f.write(s)
f.close()
# 读取
f = open("test.json", mode="r", encoding="utf-8")
for line in f:
 dic = json.loads(line.strip())
 print(dic)
f.close()

[DEFAULT] [DEFAULT]
ServerAliveInterval = 45
Compression = yes
CompressionLevel = 9
ForwardX11 = yes
[[bitbucket.org bitbucket.org]]
User = hg
[[topsecret.server.com topsecret.server.com]]
Port = 50022
ForwardX11 = no

import configparser
config = configparser.ConfigParser()
config[‘DEFAULT‘] = {
 "sleep": 1000,
 "session-time-out": 30,
 "user-alive": 999999
}
config[‘TEST-DB‘] = {
 "db_ip": "192.168.17.189",
 "port": "3306",
 "u_name": "root",
 "u_pwd": "123456"
}
config[‘168-DB‘] = {
 "db_ip": "152.163.18.168",
 "port": "3306",
 "u_name": "root",
 "u_pwd": "123456"
}
config[‘173-DB‘] = {
 "db_ip": "152.163.18.173",
 "port": "3306",
 "u_name": "root",
 "u_pwd": "123456"
}
f = open("db.ini", mode="w")
config.write(f) # 写??件
f.flush()
f.close()

config = configparser.ConfigParser()
config.read("db.ini") # 读取?件
print(config.sections()) # 获取到section. 章节...DEFAULT是给每个章节都配备的信息
print(config.get("DEFAULT", "SESSION-TIME-OUT")) # 从xxx章节中读取到xxx信息
# 也可以像字典?样操作
print(config["TEST-DB"][‘DB_IP‘])
print(config["173-DB"]["db_ip"])
for k in config[‘168-DB‘]:
 print(k)
for k, v in config["168-DB"].items():
 print(k, v)
print(config.options(‘168-DB‘)) # 同for循环,找到‘168-DB‘下所有键
print(config.items(‘168-DB‘)) #找到‘168-DB‘下所有键值对
print(config.get(‘168-DB‘,‘db_ip‘)) # 152.163.18.168 get?法Section下的
key对应的value

# 先读取. 然后修改. 最后写回?件
config = configparser.ConfigParser()
config.read("db.ini") # 读取?件
# 添加?个章节
# config.add_section("189-DB")
# config["189-DB"] = {
# "db_ip": "167.76.22.189",
# "port": "3306",
# "u_name": "root",
# "u_pwd": "123456"
# }
# 修改信息
config.set("168-DB", "db_ip", "10.10.10.168")
# 删除章节
config.remove_section("173-DB")
# 删除元素信息
config.remove_option("168-DB", "u_name")
# 写回?件
config.write(open("db.ini", mode="w"))

. 匹配除换?符以外的任意字符
\w 匹配字?或数字或下划线
\s 匹配任意的空?符
\d 匹配数字
\n 匹配?个换?符
\t 匹配?个制表符
\b 匹配?个单词的结尾
^ 匹配字符串的开始
$ 匹配字符串的结尾
\W 匹配?字?或数字或下划线
\D 匹配?数字
\S 匹配?空?符
a|b 匹配字符a或字符b
() 匹配括号内的表达式，也表示?个组
[...] 匹配字符组中的字符
[^...] 匹配除了字符组中字符的所有字符

* 重复零次或更多次
+ 重复?次或更多次
? 重复零次或?次
{n} 重复n次
{n,} 重复n次或更多次
{n,m} 重复n到m次

str: 麻花藤昨天让英雄联盟关服了
reg: 麻花藤.* 
此时匹配的是整句话

str: 麻花藤昨天让英雄联盟关服了
reg: 麻花藤.*?
此时匹配的是 麻花藤
str: <div>胡辣汤</div>
reg: <.*>
结果: <div>胡辣汤</div>
str: <div>胡辣汤</div>
reg: <.*?>
结果: 
 <div>
 </div>
str: <div>胡辣汤</div>
reg: <(div|/div*)?>
结果:
 <div>
 </div>

str: abcdefgxhijklmn
reg: .*?x
结果:abcdefgx

给出以下正则:
^[1-9]\d{13,16}[0-9x]$
^[1-9]\d{14}(\d{2}[0-9x])?$
^([1-9]\d{16}[0-9x]|[1-9]\d{14})$

lst = re.findall("m", "mai le fo len, mai ni mei!")
print(lst) # [‘m‘, ‘m‘, ‘m‘]
lst = re.findall(r"\d+", "5点之前. 你要给我5000万")
print(lst) # [‘5‘, ‘5000‘]

ret = re.search(r‘\d‘, ‘5点之前. 你要给我5000万‘).group()
print(ret) # 5

ret = re.match(‘a‘, ‘abc‘).group() 
print(ret) # a

it = re.finditer("m", "mai le fo len, mai ni mei!")
for el in it:
 print(el.group()) # 依然需要分组

ret = re.split(‘[ab]‘, ‘qwerafjbcd‘) # 先按‘a‘分割得到‘qwer‘和‘fjbcd‘,在
对‘qwer‘和‘fjbcd‘分别按‘b‘分割
print(ret) # [‘qwer‘, ‘fj‘, ‘cd‘]
ret = re.sub(r"\d+", "_sb_", "alex250taibai250wusir250ritian38") # 把字符串中
的数字换成__sb__
print(ret) # alex_sb_taibai_sb_wusir_sb_ritian_sb_
ret = re.subn(r"\d+", "_sb_", "alex250taibai250wusir250ritian38") # 将数字替
换成‘__sb__‘，返回元组(替换的结果,替换了多少次)
print(ret) # (‘alex_sb_taibai_sb_wusir_sb_ritian_sb_‘, 4)
obj = re.compile(r‘\d{3}‘) # 将正则表达式编译成为?个 正则表达式对象, 规则要匹配的
是3个数字
ret = obj.search(‘abc123eeee‘) # 正则表达式对象调?search, 参数为待匹配的字符串
print(ret.group()) # 结果: 123
爬?重点: 
obj = re.compile(r‘(?P<id>\d+)(?P<name>e+)‘) # 从正则表达式匹配的内容每个组起名
字
ret = obj.search(‘abc123eeee‘) # 搜索
print(ret.group()) # 结果: 123eeee
print(ret.group("id")) # 结果: 123 # 获取id组的内容
print(ret.group("name")) # 结果: eeee # 获取name组的内容

ret = re.findall(‘www.(baidu|oldboy).com‘, ‘www.oldboy.com‘)
print(ret) # [‘oldboy‘] 这是因为findall会优先把匹配结果组?内容返回,如果想要匹
配结果,取消权限即可
ret = re.findall(‘www.(?:baidu|oldboy).com‘, ‘www.oldboy.com‘)
print(ret) # [‘www.oldboy.com‘]

ret=re.split("\d+","eva3egon4yuan")
print(ret) #结果 ： [‘eva‘, ‘egon‘, ‘yuan‘]
ret=re.split("(\d+)","eva3egon4yuan")
print(ret) #结果 ： [‘eva‘, ‘3‘, ‘egon‘, ‘4‘, ‘yuan‘]
#在匹配部分加上（）之后所切出的结果是不同的，
#没有（）的没有保留所匹配的项，但是有（）的却能够保留了匹配的项，
#这个在某些需要保留匹配部分的使?过程是?常重要的。

import re
from urllib.request import urlopen
import ssl
# ?掉数字签名证书
ssl._create_default_https_context = ssl._create_unverified_context
def getPage(url):
 response = urlopen(url)
 return response.read().decode(‘utf-8‘)
def parsePage(s):
 ret = re.findall(
 ‘<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?
<span class="title">(?P<title>.*?)</span>‘
 ‘.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>
(?P<comment_num>.*?)评价</span>‘, s, re.S)
 return ret
def main(num):
 url = ‘https://movie.douban.com/top250?start=%s&filter=‘ % num
 response_html = getPage(url)
 ret = parsePage(response_html)
 print(ret)
count = 0
for i in range(10): # 10?
 main(count)
 count += 25

import ssl
import re
from urllib.request import urlopen
# ?掉数字签名证书
ssl._create_default_https_context = ssl._create_unverified_context
def getPage(url):
 response = urlopen(url)
 return response.read().decode(‘utf-8‘)
def parsePage(s):
 com = re.compile(
 ‘<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?
<span class="title">(?P<title>.*?)</span>‘
 ‘.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?
<span>(?P<comment_num>.*?)评价</span>‘, re.S)
 ret = com.finditer(s)
 for i in ret:
 yield {
 "id": i.group("id"),
 "title": i.group("title"),
 "rating_num": i.group("rating_num"),
 "comment_num": i.group("comment_num"),
 }
def main(num):
 url = ‘https://movie.douban.com/top250?start=%s&filter=‘ % num
 response_html = getPage(url)
 ret = parsePage(response_html)
 # print(ret)
 f = open("move_info7", "a", encoding="utf8")
 for obj in ret:
 print(obj)
 data = str(obj)
 f.write(data + "\n")
count = 0
for i in range(10):
 main(count)
 count += 25