基础函数

findall：匹配字符串中所有的符合正则的内容，返回列表

lst = re.findall(r"\d+", "我的电话是：10086，另一个是10010")
print(lst)

finditer：匹配字符串中所有的内容，返回迭代器

it = re.finditer(r"\d+", "我的电话是：10086，另一个是10010")
for i in it:
    print(i.group())

search：找到第一个匹配到的结果，返回match对象，需要group()读取数据

s = re.search(r"\d+", "我的电话是：10086，另一个是10010")
print(s.group())

match：从头开始匹配

s2 = re.match(r"\d+", "10001，我的电话是：10086，另一个是10010")
print(s2.group())

预加载正则表达式

obj = re.compile(r"\d+")
ret = obj.finditer("我的电话是：10086，另一个是10010")
for i in ret:
    print(i.group())

提取正则中的内容：(?P<分组名字>正则)，可以从正则匹配的内容中进一步提取内容

str = """
<div class='jay'><span id='1'>asd</span></div>
<div class='jj'><span id='2'>qwe</span></div>
<div class='joy'><span id='3'>ert</span></div>
<div class='tory'><span id='4'>ghj</span></div>
<div class='sylar'><span id='5'>cvb</span></div>
"""
obj1 = re.compile(r"<div class='.*?'><span id='\d+'>\w+</span>", re.S) # re.S：让.能匹配换行符
obj2 = re.compile(r"<div class='(?P<class_name>.*?)'><span id='(?P<id>\d+)'>(?P<name>\w+)</span>", re.S)

result = obj2.finditer(str)
for it in result:
    print(it.group("id"), it.group("name"))

实战1—豆瓣TOP25电影信息

  1. 拿到页面源代码:requests
  2. 通过re来提取想要的有效信息:re
import requests
import re
import csv

url = "https://movie.douban.com/top250"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36 Edg/91.0.864.64"
}

resp = requests.get(url, headers=headers)
page_content = resp.text

# 解析数据
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)'
                 r'</span>.*?<p class="">.*?<br>(?P<year>.*?)'
                 r'&nbsp;.*?<span class="rating_num" property="v:average">(?P<star>.*?)'
                 r'</span>.*?<span>(?P<num>.*?)人评价', re.S)

# 开始匹配
result = obj.finditer(page_content)
f = open("data/4_1.csv", mode="w")
csv_writer = csv.writer(f)

for it in result:
    # print(it.group("name"), it.group("year").strip(), it.group("star"), it.group("num"))
    dic = it.groupdict()
    dic['year'] = dic['year'].strip()
    csv_writer.writerow(dic.values())

f.close()
resp.close()

image-20210709143144553.png

实战2-盗版电影天堂

  1. 定位到2021必看
  2. 从必看中提取到子页面的链接地址
  3. 请求子页面的链接地址，拿到下载地址
import requests
import re

domain = "https://www.dy2018.com/"
resp = requests.get(domain, verify=False)  # verify 安全验证
resp.encoding = 'gb2312'
# print(resp.text)

# 拿到ul里面的li
obj1 = re.compile(r"2021必看热片.*?<ul>(?P<ul>.*?)</ul>", re.S)
obj2 = re.compile(r"<a href='(?P<href>.*?)'", re.S)
obj3 = re.compile(r'◎片　　名　(?P<movie>.*?)<.*?'
                  r'<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<download>.*?)">', re.S)

ret1 = obj1.finditer(resp.text)
child_href_list = []

for it in ret1:
    ul = it.group('ul')
    # 提取子页面链接
    ret2 = obj2.finditer(ul)
    for it2 in ret2:
        # 拼接子页面：域名+子页面地址
        child_href = domain + it2.group('href').strip("/")
        # 保存子页面地址
        child_href_list.append(child_href)

# 提取子页面内容
for href in child_href_list:
    child_resp = requests.get(href, verify=False)
    child_resp.encoding = 'gb2312'
    ret3 = obj3.search(child_resp.text)
    print(ret3.group("movie"))
    print(ret3.group("download"))

resp.close()

image-20210709145007924.png