Crawler data analysis (introduction 2-re analysis)

re analysis

Regular test site   Online regular expression testing

 

Code example

import re
# #findall
# lst = re.findall(r"\d+", " My phone number is 10086, My girlfriend's phone number is 10010")
# print(lst)

# #finditer
# it=re.finditer(r"\d+"," My phone number is 10086, My girlfriend's phone number is 10010")
# for i in it:
#     print(i)
#     print(i.group())

# #search Looking for the first  .group() Get data 
# s=re.search(r"\d+"," My phone number is 10086, My girlfriend's phone number is 10010")
# print(s.group())

#match Match from the beginning 
# s=re.match(r"\d+","10086, My girlfriend's phone number is 10010")
# print(s.group())

# # Preload regular expressions 
# obj=re.compile(r"\d+")
# ret=obj.finditer(" My phone number is 10086, My girlfriend's phone number is 10010")
# for it in ret:
#     print(it.group())
#
# ret2=obj.findall("hhh Hahaha, East China and Wuhan 1000000000000000")
# print(ret2)

s = """
<div class='jay'><span id='1'> China Unicom </span></div>
<div class='ja'><span id='2'> China Mobile </span></div>
<div class='jy'><span id='3'> China Telecom </span></div>
<div class='jpl'><span id='4'> an old China hand </span></div>
<div class='jal'><span id='5'> China Federation </span></div>
"""
#(?P< Group name > Regular ) Further information can be extracted from the regular content alone 
obj=re.compile(r"<div class='.*?'><span id='(?P<id>\d+)'>(?P<wahaha>.*?)</span></div>",re.S)#re.S  Give Way . Can match newline 
ret=obj.finditer(s)
for it in ret:
    print(it.group("id"))
    print(it.group("wahaha"))