python re模块正则表达式

re的工作是在python中执行正则表达式
import re

# find
result = re.findall('\d+', 'baby的电话号是:185123456789')
print(result)
#
it = re.finditer('\d+','baby的电话号是:185123456789')
for i in it:
    print(i.group()) # 分组

# search 搜索, 查找
# 一旦匹配到结果. 直接返回, 如果匹配不到结果. 返回None
result = re.search('\d','baby的电话号是:185123456789')
print(result)
print(result.group())
#
#
# match 匹配, 从头开始匹配. 相当于在你正则前面加了一个^
result = re.match('\d+','185123456789baby的电话号是:')
print(result.group())

# search和match的区别: search查找. 找到了结果就返回. match 从头开始匹配

result = re.finditer(r'姓名:(?P<name>.*?),爱好:(?P<hobby>.*?),', '姓名:宝宝,爱好:女,性格开朗大方')
for i in result:
    print(i.group('name'), i.group('hobby'))

简单爬虫

from urllib.request import urlopen

content = urlopen("https://www.dytt8.net/html/gndy/dyzz/20181219/57954.html").read().decode("gbk")
# print(content)

reg = r'<div id="Zoom">.*?片　　名(?P<name>.*?)<br />◎年　　代(?P<years>.*?)<br />.*?◎上映日期(?P<date>.*?)<br />'+ \
'.*?◎主　　演(?P<main>.*?)◎简　　介.*?<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<download>.*?)">'

it = re.finditer(reg, content, re.S) # re.S 去掉.里面的\n

for el in it:
    print(el.group())