python 手机靓号的识别与提取

一、提取1

import re

str="15838477645dfdfdf15887988765dfdf1157990087651fd157385367891fdf15826789876qqq15838545678a"

#方法一：限制手机号开头，或者手机号前面为非数字，且手机号结尾或者以非数字结尾
pattern1="(?:^|[^\d])(1\d{10})(?:$|[^\d])"
phone_list1=re.compile(pattern1).findall(str)

#方法二：利用负向零宽断言，断言手机号前后不能出现数字
pattern2="(?<!\d)(1\d{10})(?!\d)"
phone_list2=re.compile(pattern2).findall(str)

print('phone_list1:',phone_list1)
print('phone_list2:',phone_list2)

二、提取2

import requests
import re
from bs4 import BeautifulSoup

def down():
    r = requests.get("http://www.haomahao.com/") #调用网页
    r.encoding = r.apparent_encoding             #更改网页编码，防止出现乱码
    #print(r.text)
    bs = BeautifulSoup(r.text,"html.parser")
    str1 = bs.getText()                          #将BeautifulSoup提出出来的写完text
    parttern = "1[35789]\d{9}"                   #编写手机号的正则表达式
    list = re.findall(parttern,str1)
                                                 #print(list) #调试正则是否正确
 
    f = open("手机号.txt",mode="w",encoding="utf-8") #写入文件
    f.write("\n".join(list))
    f.close()
if __name__ == "__main__":
    down()

三、提取3

import re
 
# 正则匹配手机号
def judge_phone_number(account):
    a = re.findall('(13\d{9}|14[5|7]\d{8}|15\d{9}|166{\d{8}|17[3|6|7]{\d{8}|18\d{9})', account)
    return a

if __name__ == '__main__':
    s = judge_phone_number('asdasdasdasd15319547777sdfs')
    print(s)
#############################################################################
import re
 
# 正则匹配手机号
def judge_phone_number(account):
    a = re.findall('(1.*?)sdfs', account)
    return a

if __name__ == '__main__':
    s = judge_phone_number('asdasdasdasd15319547777sdfs')
    print(s)
###########################################################################
import re
 
# 正则匹配手机号
def judge_phone_number(account):
    a = re.findall('(1.*?7777)', account)
    return a

if __name__ == '__main__':
    s = judge_phone_number('asdasdasdasd15319547777sdfs')
    print(s)

四、提取4

# -*- coding:utf-8 -*-
import re

# 验证手机号是否正确

phone_pat = re.compile('^(13\d|14[5|7]|15\d|166|17[3|6|7]|18\d)\d{8}$')

while True:
    phone = input('请输入您的手机号:')

    res = re.search(phone_pat, phone)
    if res:
        print('正常手机号')
    else:
        print('不是手机号')

五、提取5

import re


def main():
    tel = input("请输入手机号:")
    # ret = re.match(r"1[35678]\d{9}", tel)
    # 由于手机号位数大于11位也能匹配成功，所以修改如下：
    ret = re.match(r"^1[35678]\d{9}$", tel)

    if ret:
        print("匹配成功")
    else:
        print("匹配失败")

if __name__ == "__main__":
    main()
   #########################################################
 import re


def main():
    tel = input("请输入手机号:")
    ret = re.match(r"^1[35678]\d{9}$", tel)

    if ret:
        print("匹配成功")
    else:
        print("匹配失败")

if __name__ == "__main__":
    main()
##################################################################
import re
 
def main(ori_str):
    strings = re.finditer(r'(.)\1', ori_str)         # 匹配AA
    for i in strings:
        print('AA=',i)
    strings = re.finditer(r'(.)\1{2}', ori_str)      # 匹配AAA
    for i in strings:
        print('AAA=',i)
    strings = re.finditer(r'(.)\1(.)\2', ori_str)    # 匹配AABB
    for i in strings:
        print('AABB=',i)
    strings = re.finditer(r'(((.).\3.)|((.)\5(.)\6))', ori_str)    # 匹配ABAB
    for i in strings:
        print('ABAB=',i)
    strings = re.finditer(r'(.)\1{3}', ori_str)    # 匹配AAAA
    for i in strings:
        print('AAAA=',i)      
    
if __name__ == '__main__':
    main('17733337474')
 ######################################################################
 from re import findall
text = '''行尸走肉、金蝉脱壳、百里挑一、金玉满堂、
背水一战、霸王别姬、天上人间、不吐不快、海阔天空、
情非得已、满腹经纶、兵临城下、春暖花开、插翅难逃、
黄道吉日、天下无双、偷天换日、两小无猜、卧虎藏龙、
珠光宝气、簪缨世族、花花公子、绘声绘影、国色天香、
相亲相爱、八仙过海、金玉良缘、掌上明珠、皆大欢喜、
浩浩荡荡、平平安安、秀秀气气、斯斯文文、高高兴兴'''
print("全部词语： ", text)
pattern = r'(((.).\3.)|((.)\5(.)\6))'
print("匹配ABAC和AABB的词语：", list(i[0] for i in findall(pattern, text)))

六、提取6

import pandas as pd
import csv
import re
class PhoneMatch(object):
    def __init__(self, file_path) -> None:
        self.file_path = file_path
    def look_name(self,data):
        subData = data.loc[(data['联系方式名'] == data['法人名'])]
        return subData
    def phone_number_match(self, phone):
        string1 = re.findall(r"(\d)\1\1(?!\1)\d", str(phone)) # AAAB
        if len(string1) >= 1:
            return True
        string2 = re.findall(r'(.)\1(.)\2', str(phone)) #AABB
        if len(string2) >= 1:
            return True
        string3 = re.findall(r'(\w\w)\1+', str(phone)) #ABAB
        if len(string3) >= 1:
            return True
        string4 = re.findall(r"(\w)\1{3}", str(phone)) #AAAA
        if len(string4) >= 1:
            return True
        # ABCD
        string5 = re.findall(r"(?:0(?=1)|1(?=2)|2(?=3)|3(?=4)|4(?=5)|5(?=6)|6(?=7)|7(?=8)|8(?=9)){3}\d", str(phone)) #AAAA
        if len(string5) >= 1:
            return True
        # DCBA
        string6 = re.findall(r"(?:9(?=8)|8(?=7)|7(?=6)|6(?=5)|5(?=4)|4(?=3)|3(?=2)|2(?=1)|1(?=0)){3}\d", str(phone)) #AAAA
        if len(string6) >= 1:
            return True
    def run(self,):
        data = pd.read_csv(self.file_path)
        # drop_index = [i for i in data["电话"].index if not self.phone_number_match(data["电话"][i])]
        # n_data = data.drop(drop_index)
        h = self.look_name(data)
        drop_index = []
        for i in data["电话"].index:
            if not self.phone_number_match(data["电话"][i]):
                drop_index.append(i)
        n_data = data.drop(drop_index)
        df = pd.concat([n_data, h])
        return df
if __name__ == "__main__":
    ph = PhoneMatch("./tell.csv")
    g = ph.run()
    print(len(g))
    g.to_csv('./tellss.csv',index=False)