标签：re Python text day07 武沛齐 path print import os

day07 模块

1.知识回顾
• 模块的分类
- 自定义模块

• 内置
• 第三方模块
  • 自定义模块
  – 关于拆分
  crm
• utils
  • encrypt.py
  • db.py
  • message.py
• app.py
  – 文件夹和文件（扩展）
  py文件 -> 模块
  文件夹 -> 包
  py2的包：内部必须有一个 init.py
  py3的包：无限制
  – 导入模块
  • 去哪里导入？
  import sys

sys.path
当前运行脚本所在目录
python的安装目录
python的安装目录/site-packages

注意：pycharm自动将项目目录加入sys.path【应该忽略】
• 怎么导入？
import ???
from xxxx.xxxx import ???
from xxxx.xxxx import *
from xxxx.xxxx import xxx
from xxxx.xxxx import xxx as ???
from xxxx.xxxx import xxx,xx,x
– 主文件+主函数
def func():
pass

func()
def func():
pass

if name == "main":
func()
当一个py文件被运行时，__name__就是"main"
当一个py文件被导入时，__name__就是模块的名字，例如：utils.xxx.info
• 内置模块
– random
– hashlib
– json
– time/datetime
– os

2.内置模块
2.1 os
• 路径拼接
import os

path = os.path.join("xxx","xxxx","xxxxx","xxxx.txt")
• 上级目录
import os

path = os.path.dirname(".....")
• 绝对路径
import os

os.path.abspath(".....")
os.path.abspath(file)
import os

base_dir = os.path.dirname(os.path.abspath(file))
• 判断路径是否存在
import os

v1 = os.path.exists("路径")
print(v1) # True/False
import os

user = input("用户名:")

file_path = os.path.join("files", "db.txt")

判断文件夹是否存在？

if os.path.exists(os.path.dirname(file_path)):
with open(file_path, mode='a', encoding='utf-8') as f:
f.write(f"{user}\n")
else:
print("路径不存在")
import os

file_path = os.path.join("files", 'db.txt')

if os.path.exists(file_path):

with open(file_path, mode='r', encoding='utf-8') as f:
    data = f.read()
    print(data)

else:
print("文件不存在")
• 创建文件夹（文件夹不存在）
import os

os.makedirs("xxx/xxxx/xxxx")
import os

user = input("用户名:")

file_path = os.path.join("files", "db.txt")

folder_path = os.path.dirname(file_path)
if not os.path.exists(folder_path):
os.makedirs(folder_path)

with open(file_path, mode='a', encoding='utf-8') as f:
f.write(f"{user}\n")
import os.path

import requests
from datetime import datetime

pip install requests

url_list = [
"https://www3.autoimg.cn/newsdfs/g30/M05/3C/5E/400x300_0_autohomecar__ChxknGRTwLSAP9MuAAA6hd6ZZDY038.jpg",
"https://www3.autoimg.cn/cubetopic/g27/M04/43/F9/400x300_0_autohomecar__ChxkmWRTWkaACfQbAADCg_L8aQM773.jpg"
]

for url in url_list:
res = requests.get(url=url)
# 图片写入本地文件
date_string = datetime.now().strftime("%Y-%m-%d")
name = url.split("__")[-1]

if not os.path.exists(date_string):
    os.makedirs(date_string)

file_path = os.path.join(date_string, name)
with open(file_path, mode='wb') as f:
    f.write(res.content)

• 判断文件 或 文件夹
os.path.isdir(...)
• 删除文件和文件夹
import os

os.remove("文件路径") # 删除文件
import shutil

shutil.rmtree("文件夹的路径") # 删除文件夹
• 查看目录下的文件或文件夹【一级目录】
import os

name_list = os.listdir("路径")
import os.path

folder_path = os.path.join("2023-05-05")

name_list = os.listdir(folder_path)
for name in name_list:
inner_path = os.path.join(folder_path,name)
if os.path.isdir(inner_path):
print(os.listdir(inner_path))
else:
print(inner_path)
• 查看目录下的文件或文件夹【多级目录】
import

os.walk("路径")
import os

folder_path = os.path.join("2023-05-05")
for base_dir, folder_list, file_list in os.walk(folder_path):
for name in file_list:
file_path = os.path.join(base_dir,name)
print(file_path)

import os

folder_path = os.path.join(r"E:\EvVideo\其他视频")
for base_dir, folder_list, file_list in os.walk(folder_path):
for name in file_list:
if not name.endswith(".mp4"):
continue
file_path = os.path.join(base_dir, name)
print(file_path)

案例：用户注册

• 输入：用户名+密码（md5加密）
• 写入文件
  2023-11-11
  12-09.txt
  12-10.txt
  2023-11-12
  12-09.txt
  12-10.txt
  import hashlib
  import os.path
  from datetime import datetime

MD5_SALT = "asdfasdkfojlkjao9urpqoiwj;lkafjsdf"

def md5(data_str):
obj = hashlib.md5(MD5_SALT.encode('utf-8'))
obj.update(data_str.encode('utf-8'))
return obj.hexdigest()

def gen_file_path():
ctime = datetime.now()
date_string = ctime.strftime("%Y-%m-%d")
time_string = ctime.strftime("%H-%M")

# 3.1 文件夹处理
if not os.path.exists(date_string):
    os.makedirs(date_string)
# 3.2 文件路径
file_path = os.path.join(date_string, f"{time_string}.txt")
return file_path

def run():
# 1.输入用户名和密码
user = input("用户名：")
pwd = input("密码：")
md5_pwd = md5(pwd)

# 2.拼接
line = f"{user},{md5_pwd}\n"

# 3.创建路径+写入
file_path = gen_file_path()
with open(file_path, mode='a', encoding='utf-8') as f:
    f.write(line)

if name == 'main':
run()
1分钟就会生成1个文件，

2.2 sys
import sys

1.导入模块时，都会去哪里找

sys.path

2.sys.argv，运行脚本时传入的参数

sys.argv

这东西有什么用？
• IT相关同学：shell脚本
• 非IT相关的同学
写程序去实现下载某个视频的一个需求。

• 方式1：input来实现
  url = input("请输入下载网址：")
• 方式2：argv
  import sys
  url = sys.argv[1]
  print("下载：", url)

2.3 打包代码
pip3.9 install pyinstaller

2.3.1 多文件打包
pyinstaller -D client.py

2.3.2 单文件打包（喜欢）
pyinstaller -F client.py
如果你的程序中会涉及到文件的操作，文件放在项目的相对目录。【BUG】

当运行 client.exe 文件时，内部有很多的代码，会放在电脑的临时目录。

os.path.abspath(file)

C:\Users\ADMINI~1\AppData\Local\Temp_MEI77322\client.py

• 如果使用的【绝对路径】+【file】 【错误】
import os

def run():
base_dir = os.path.dirname(os.path.abspath(file))
db_file_path = os.path.join(base_dir, "db.txt")
with open(db_file_path, mode='r', encoding='utf-8') as f:
print(f.read())

user = input("用户名：")
pwd = input("密码：")

line = f"{user},{pwd}"
print(line)

input("回车继续")

if name == 'main':
run()

双击的话，一闪而过
把文件拖到cmd里就能如上面看到报错

• 如果使用的【绝对路径】+【sys.argv】 【正确】
import os
import sys

def run():
base_dir = os.path.dirname(sys.argv[0])
db_file_path = os.path.join(base_dir, "db.txt")
with open(db_file_path, mode='r', encoding='utf-8') as f:
print(f.read())

user = input("用户名：")
pwd = input("密码：")

line = f"{user},{pwd}"
print(line)

input("回车继续")

if name == 'main':
run()

• 相对路径 【正确】
def run():
with open("db.txt", mode='r', encoding='utf-8') as f:
print(f.read())

user = input("用户名：")
pwd = input("密码：")

line = f"{user},{pwd}"
print(line)

input("回车继续")

if name == 'main':
run()

小结
后期如果你的项目需要读取文件 + 文件夹 等需求，推荐使用绝对路径。
• 开发阶段：代码运行
• 打包阶段：exe运行
import os
import sys

BASE_DIR = os.path.dirname(os.path.realpath(sys.argv[0]))

def run():
with open(os.path.join(BASE_DIR,'db.txt'), mode='r', encoding='utf-8') as f:
print(f.read())

user = input("用户名：")
pwd = input("密码：")

line = f"{user},{pwd}"
print(line)

input("回车继续")

if name == 'main':
run()

2.3 configparser
• 用txt文件【配置文件操作】
xxx=123
xxxx=123
• 专门用于对于 .ini 格式的文件【一般用于项目的配置文件】 *
[server]
v1=123
v2=456

[client]
v9=111
• 使用JSON格式 .json格式 【一般用于项目的配置文件】
{
"count":123,
"info":[11,22,33]
}
• 专门使用xml格式文件【一般用于项目的配置文件】
123
123
• Python的模块 settings.py 【无法再打包后进行修改生效】
COUNT = 123
INFO = 999

2.3.1 基本操作
import configparser

1.打开并读取文件

obj = configparser.ConfigParser()
obj.read("my.ini", encoding='utf-8')

2.读取节点

v1 = obj.sections()

print(v1)

[‘server’,’client’]

3.键值对

v2 = obj.items("server")

for k,v in v2:

print(k,v)

v2

4.键值

v3 = obj.get("server",'v3')

print(v3)

中国联通

5.包含

v3 = obj.has_section("server")

print(v3)

True

6.添加

obj.add_section("group")

obj.set("group", 'name', "武沛齐")

obj.set("group", 'age', "19")

with open("my.ini", mode='w', encoding='utf-8') as f:

obj.write(f)

7.删除

obj.remove_section("group")

with open("my.ini", mode='w', encoding='utf-8') as f:

obj.write(f)

8.删除

obj.remove_option("server", "v2")

with open("my.ini", mode='w', encoding='utf-8') as f:

obj.write(f)

9.修改

obj.set("server", "v1", "999")

with open("my.ini", mode='w', encoding='utf-8') as f:

obj.write(f)

2.3.2 应用案例

1.价格监测平台
通过爬虫的程序，一直请求网页，查看他得价格。一旦低于我的预期，我就进行消息的通知。
监测过程中需求配置：
• 间隔时间：30
• 企业微信：群 + 群机器人 + 网址发送

import configparser
import os
import sys

BASE_DIR = os.path.dirname(os.path.realpath(sys.argv[0]))
SETTINGS_PATH = os.path.join(BASE_DIR, 'my.ini')

def run():
# 1.加载配置文件
# 1.1 找到文件
if not os.path.exists(SETTINGS_PATH):
print("配置文件不存在")
input("")
return
# 2.2 读取
config_dict = {}
config = configparser.ConfigParser()
config.read(SETTINGS_PATH, encoding='utf-8')

for k, v in config.items("server"):
    config_dict[k] = v

# 2.根据配置编写代码
print(config_dict)
input("功能实现...")
input("回车继续")

if name == 'main':
run()
打包后要把my.ini放在dist下，和client.exe放在一起，才能正常运行，不放一起的话，会提示配置文件不存在，然后退出

import configparser
import os
import sys
import time
import requests

BASE_DIR = os.path.dirname(os.path.realpath(sys.argv[0]))
SETTINGS_PATH = os.path.join(BASE_DIR, 'my.ini')

def fetch_new_info():
return True

def run():
# 1.加载配置文件
# 1.1 找到文件
if not os.path.exists(SETTINGS_PATH):
print("配置文件不存在")
input("")
return
# 2.2 读取
config_dict = {}
config = configparser.ConfigParser()
config.read(SETTINGS_PATH, encoding='utf-8')

for k, v in config.items("server"):
    config_dict[k] = v

# 2.根据配置编写代码
print(config_dict)
interval = int(config_dict["interval"])
while True:
    status = fetch_new_info()
    if status:
        break

    time.sleep(interval)

# 3.消息通知 [企业微信]+[群]+[机器人]
# https://www.zhihu.com/question/395840381/answer/2278274881
notify_url = config_dict['notify']

input("功能实现...")
input("回车继续")

if name == 'main':
run()

import configparser
import os
import sys
import time
import requests

BASE_DIR = os.path.dirname(os.path.realpath(sys.argv[0]))
SETTINGS_PATH = os.path.join(BASE_DIR, 'my.ini')

CONFIG_DICT = None

def fetch_new_info():
return True

def process():
print(CONFIG_DICT)
interval = int(CONFIG_DICT["interval"])
while True:
status = fetch_new_info()
if status:
break

    time.sleep(interval)

def notify():
# https://www.zhihu.com/question/395840381/answer/2278274881
notify_url = CONFIG_DICT['notify']

def load_config():
# 1.1 找到文件
if not os.path.exists(SETTINGS_PATH):
return False, "配置文件不存在"
# 2.2 读取
config_dict = {}
config = configparser.ConfigParser()
config.read(SETTINGS_PATH, encoding='utf-8')

for k, v in config.items("server"):
    config_dict[k] = v
return True, config_dict

def run():
# 1.加载配置文件
status, config_dict = load_config()
if not status:
print(config_dict)
input("")
return

global CONFIG_DICT
CONFIG_DICT = config_dict

# 2.根据配置编写代码
process()

# 3.消息通知 [企业微信]+[群]+[机器人]
notify()

input("功能实现...")
input("回车继续")

if name == 'main':
run()

2.4 XML
一种特殊的格式，用于表示和存储数据。

武沛齐
18

{
"name":"武沛齐",
"age":18
}

text = """


2
2023
141100




69
2026
13600




"""

from xml.etree import ElementTree

root = ElementTree.XML(text)

1.第一个

node = root.find("country")

print(node)

print(node.tag)

print(node.attrib)

2.找到多个

node_list = root.findall("country")

for node in node_list:

print(node.tag, node.attrib)

3.继续向下找

node_list = root.findall("country")
for node in node_list:
# print(node.tag, node.attrib)
# res = node.getchildren()
# print(res)
# rank = node.find("rank")
# print(rank.text, rank.attrib)

for child in node:
    print(child.tag, child.text, child.attrib)

案例：腾讯接口API
from xml.etree import ElementTree

text = """

武沛齐
root
1348831860
text
吃饭了
1234567890123456
xxxx
11

"""

data_dict = {}
root = ElementTree.XML(text)
for node in root:
data_dict[node.tag] = node.text
print(data_dict)

2.5 re模块
• 正则表达式，提取or校验你的数据。
• re模块Python中的内置模块，用于和正则表达式搭配。

2.5.1 正则表达式
text = "楼主太牛逼了，在线想要 [email protected] 和 [email protected]谢谢楼主，手机号也可15131255789，搞起来呀"

需求：提取手机号 \d{11}
需求：提取邮箱 \w+@\w+.\w+
text = "楼主太牛逼了，在15131255781线想要 [email protected] 和 [email protected]谢谢楼主，手机号也可15131255789，搞起来呀"

import re

ret = re.findall(r"\d{11}", text)
print(ret)
text = "楼主太牛逼了，在15131255781线想要 [email protected] 和 [email protected]谢谢楼主，手机号也可15131255789，搞起来呀"

import re

ret = re.findall(r"\w+@\w+.\w+", text, re.ASCII)
print(ret)

email = input("邮箱：")

import re

ret = re.match(r"^\w+@\w+.\w+$", email)
if ret:
print("格式合法")
else:
print("格式错误")

1.字符相关
• 固定文本
import re

text = "你好wupeiqi,阿斯顿发wupeiqasd 阿士大夫能接受的wupeiqiff"

data_list = re.findall(r"wupeiqi", text)

print(data_list) # ["wupeiqi", "wupeiqi"]
• 含有特定字符串
import re

text = "你好wupeiqi,阿斯顿发wupeiqasd 阿士大夫能接受的wupeiqbiff"

wupeiqa wupeiqb wupeiqi

data_list = re.findall(r"wupeiq[abi]", text)

print(data_list) # ["wupeiqi", "wupeiqa","wupeiqb"]
• 范围 [a-z] [0-9]
import re

text = "你好twupeiqi,阿斯顿发wupetiqasd 阿士大夫能接受的wutpeiqbff"

data_list = re.findall(r"t[a-z]", text)

print(data_list) # ['tw', 'ti', 'tp']
import re

text = "你好twupeiqi,阿斯顿发wupet2iqasd 阿士大夫能接受的wut1peiqbff"

data_list = re.findall(r"t[0-9]", text)

print(data_list)
import re

text = "你好twupeiqi,阿斯顿发wupet2iqasd 阿士大夫能接受的wut1peiqbff"

data_list = re.findall(r"t[0-9][a-z]", text)

print(data_list)
• \d 数字
import re

text = "你好t11wupeiqi,阿斯顿发wupet22iqasd 阿士大夫能接受的wut8peiqbff"

data_list = re.findall(r"t\d", text)

print(data_list) # ['t1', 't2', 't8']
import re

text = "你好t11wupeiqi,阿斯顿发wupet22iqasd 阿士大夫能接受的wut8peiqbff"

data_list = re.findall(r"t\d\d", text)

print(data_list) # ['t11', 't22']
• \w，字母、数字、下划线（汉字）
text = "你t好t11wupeiqi,阿斯顿发wupet21232123iqasd 阿s顿大夫能接受的wut8peiqbff"

import re

result = re.findall(r"阿\w顿",text)

print(result) # ['阿斯顿', '阿s顿']
text = "你t好t11wupeiqi,阿斯顿发wupet21232123iqasd 阿s顿大夫能接受的wut8peiqbff"

import re

result = re.findall(r"阿\w顿",text,re.ASCII)

print(result) # ['阿s顿']
• . 除换行符以外的任意字符
text = "你t好t11wupeiqi,阿斯顿发wupet21232123iqasd 阿s顿大夫能接受的阿\n顿ut8peiqbff"

import re

result = re.findall(r"阿.顿", text)

print(result) # ['阿斯顿', '阿s顿']

2.数量先关
• {n}
• {n,}
• {n,m}
• *，0次或n次
import re

text = "你好t1wupeiqi,阿斯顿发wupetwdiqasd 阿士大夫能接受的wut18weiqbff"

data_list = re.findall(r"t\d*w", text)

print(data_list) # ['t1w', 'tw', 't18w']
• +，1次或n次
import re

text = "你好t1wupeiqi,阿斯顿发wupetwdiqasd 阿士大夫能接受的wut18weiqbff"

data_list = re.findall(r"t\d+w", text)

print(data_list) # ['t1w', 't18w']
• ?，0次或1次
import re

text = "你好t1wupeiqi,阿斯顿发wupetwdiqasd 阿士大夫能接受的wut18weiqbff"

data_list = re.findall(r"t\d?w", text)

print(data_list) # ['t1w', 'tw']

3.分组
• 在正则中匹配成功，再去提取局部数据。
import re

text = "楼主太牛逼了，在线想要 [email protected]和[email protected]谢谢楼主，手机号也可15131255799，搞起15131255989来呀"

result = re.findall(r"(151(312\d{5}))", text)
print(result)

[('15131255799', '31255799'), ('15131255989', '31255989')]

import re

text = "我的身份证130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

res = re.findall('\d{17}[\dX]', text)
print(res)
import re

text = "我的身份证130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

res = re.findall('\d{6}\d{4}\d{2}\d{2}\d{3}[\dX]', text)
print(res)
import re

text = "我的身份证130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

res = re.findall('(\d{6}(\d{4})(\d{2})(\d{2})\d{3}[\dX])', text)
print(res)
• 表示或
import re

text = "楼主15131root太牛15131alex逼了，在线想要 [email protected]和[email protected]谢谢楼主，手机号也可15131255789，搞起来呀"

data_list = re.findall(r"15131(2\d{5}|r\w+太)", text)

print(data_list)

4.起始和结束
import re

text = "130449197912038879"

res = re.findall(r'^\d{17}[\dX]$', text)
print(res)

案例
• 身份证号码
import re

text = "dsf130429191912015219k13042919591219521Xkk"
data_list = re.findall(r"\d{17}[\dX]", text)
print(data_list)
• 手机号
import re

text = "我的手机哈是15133377892，你的手机号是1171123啊？"
data_list = re.findall(r"1[3-9]\d{9}", text)
print(data_list)
• 邮箱
import re

text = "楼主太牛逼了，在线想要 [email protected]和[email protected]谢谢楼主，手机号也可15131255789，搞起来呀"
email_list = re.findall(r"\w+@\w+.\w+", text, re.ASCII)
print(email_list)
import re

text = "楼主太牛逼了，在线想要 [email protected]和[email protected]谢谢楼主，手机号也可15131255789，搞起来呀"

email_list = re.findall(r"[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+.[a-zA-Z0-9_-]+", text)
print(email_list)

2.5.2 re模块
• re.findall，去整个文本中找所有符合正则条件的文本。
import re

text = "我的身份证130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

res = re.findall('\d{17}[\dX]', text)
print(res) # ['130449197912038879', '13044919991203887X']
• re.search，去整个文本去匹配，返回匹配成功的第一个
import re

text = "我的身份证130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

match_object = re.search('\d{17}[\dX]', text)
print(match_object.group()) # 130449197912038879
• re.match，从开始位置进行匹配，返回匹配成功的第一个
import re

text = "130449197912038879,郭智的身份之是13044919991203887X阿斯顿发士大夫"

match_object = re.match('\d{17}[\dX]', text)
print(match_object)
if match_object:
print(match_object.group()) # 130449197912038879
else:
print("失败")
• re.split
text = "武沛齐,123"

data_list = text.split(",")
print(data_list) # ["武沛齐","123"]
import re

text = "武沛齐,123"

data = re.split(r",",text)
print(data)
import re

text = "武沛齐,123-999"

data = re.split(r"[,-]", text)
print(data)

案例：片段

import re

price = "￥5499"

ret = re.findall(r"￥(\d+)",price)
print(ret)

text = "已有2人评价"
ret = re.findall(r"已有(\d+)人评价",text)
print(ret)

3.第三方模块
优秀开发者，开源出来一个模块，供其他使用。

• 使用者：左边
• 开源者：https://www.bilibili.com/video/BV17541187de/

常见命令：
pip install requests
pip uninstall requests
pip list
pip freeze > requirements.txt
pip install -r requirements.txt

配置pip源：
pip3.9 config set global.index-url https://pypi.douban.com/simple/
pip install ???

2.1 requests模块
基于代码实现发送网络请求。
pip install requests

2.1.1 分析请求 + 实现 + json

Request URL: https://www.zhihu.com/api/v4/comment_v5/articles/545093058/root_comment?order_by=score&limit=20&offset=

Request Method: GET

import json
import requests

res = requests.get(
url="https://www.zhihu.com/api/v4/comment_v5/articles/545093058/root_comment?order_by=score&limit=20&offset="
)

data_dict = json.loads(res.text)
for row in data_dict['data']:
content = row['content']
name = row['author']['name']

print(name, content)

2.1.2 分析请求 + 实现 + json
import requests
import json

res = requests.get(
url="https://movie.douban.com/j/search_subjects?type=movie&tag=豆瓣高分&sort=recommend&page_limit=20&page_start=20",
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
}
)

data_dict = json.loads(res.text)
for row in data_dict['subjects']:
print(row['title'], row['url'])

2.1.3 数据返回值-JSONP格式
• JSON格式，最容易处理

res = reque...

data_dict = json.loads(res.text)
data_dict = res.json()
• JSONP格式
名字({"rate":"9.0","cover_x":1500,"title":"让子弹飞"})
– 去除元素
名字({"rate":"9.0","cover_x":1500,"title":"让子弹飞"})

{"rate":"9.0","cover_x":1500,"title":"让子弹飞"}
– eval，将一段字符串当做python代码进行编译执行。
def demo(arg):
print(arg)

eval('demo({"rate":"9.0","cover_x":1500,"title":"让子弹飞"})')

import json

import requests

res = requests.get(
url="http://num.10010.com/NumApp/NumberCenter/qryNum?callback=jsonp_queryMoreNums&provinceCode=11&cityCode=110&advancePayLower=0&sortType=1&goodsNet=4&searchCategory=3&qryType=02&channel=B2C&numNet=186&groupKey=53271060&judgeType=1"
)

content = res.text

字符串处理

result = content.strip("jsonp_queryMoreNums(").strip(")")

print(result)

data_dict = json.loads(result)
print(data_dict)
import json

import requests

def jsonp_queryMoreNums(data_dict):
print(data_dict)

res = requests.get(
url="http://num.10010.com/NumApp/NumberCenter/qryNum?callback=jsonp_queryMoreNums&provinceCode=11&cityCode=110&advancePayLower=0&sortType=1&goodsNet=4&searchCategory=3&qryType=02&channel=B2C&numNet=186&groupKey=53271060&judgeType=1"
)

content = res.text

字符串处理

eval(content)

2.1.4 HTML格式
你看到网站的所有的内容，本质上都是由HTML标签给他包裹。

中国联通 青海 广西 广东 pip install BeautifulSoup4 import requests from bs4 import BeautifulSoup

res = requests.get(
url="https://www.autohome.com.cn/news/"
)
res.encoding = 'gb2312'

print(res.text)

1.将文本交给BeautifulSoup进行处理

soup = BeautifulSoup(res.text, features="html.parser")

2.使用对象就是整个文本根据特征寻找标签

tag = soup.find(name="div", attrs={"id": "auto-channel-lazyload-article"})

3.继续往下找

li_list = tag.find_all(name="li")
for node in li_list:
h3_tag = node.find(name="h3")
if not h3_tag:
continue

p_tag = node.find(name="p")
img_tag = node.find(name='img')

print(h3_tag.text)
print(p_tag.text)
print(img_tag.attrs['src'])

print('------------------')

import requests
from bs4 import BeautifulSoup

res = requests.get(
url="https://www.autohome.com.cn/news/"
)
res.encoding = 'gb2312'

print(res.text)

1.将文本交给BeautifulSoup进行处理

soup = BeautifulSoup(res.text, features="html.parser")

2.使用对象就是整个文本根据特征寻找标签

tag = soup.find(name="ul", attrs={"id": "tagInfo"})

3.每个元素

node_list = tag.find_all(name="li")
for li_node in node_list:
name = li_node.find(name="div", attrs={"class": "editorname"}).text
src = li_node.find(name='img').attrs['src']
src_url = f"https:{src}"
print(name, src_url)

import requests
from bs4 import BeautifulSoup

res = requests.get(
url="https://www.autohome.com.cn/news/"
)
res.encoding = 'gb2312'

print(res.text)

1.将文本交给BeautifulSoup进行处理

soup = BeautifulSoup(res.text, features="html.parser")

2.使用对象就是整个文本根据特征寻找标签

tag = soup.find(name="ul", attrs={"id": "tagInfo"})

3.每个元素

node_list = tag.find_all(name="li")
for li_node in node_list:
name = li_node.find(name="div", attrs={"class": "editorname"}).text
src = li_node.find(name='img').attrs['src']
src_url = f"https:{src}"
print(name, src_url)

# 根据URL去发送请求，下载图片的内容
response = requests.get(url=src_url)
with open(f"{name}.jpg",mode='wb') as f:
    f.write(response.content)

案例：联通商品商城
import requests
from bs4 import BeautifulSoup

1.发送网络请求，获取文本数据

res = requests.get(
url="http://s.10010.com/bj/mobile/"
)

print(res.text)

2.解析数据bs4

soup = BeautifulSoup(res.text, features="html.parser")

3.寻找特征+获取内部元素

tag = soup.find(name='div', attrs={'id': "goodsList"})

4.寻找每个商品

li_list = tag.find_all(name='li', attrs={"class": 'goodsLi'})
for li_node in li_list:
title = li_node.find(name='p', attrs={"class": "mobileGoodsName"}).text.strip()
price = li_node.find(name='p', attrs={"class": "evaluation"}).text.strip()
comment = li_node.find(name='p', attrs={"class": "evalNum"}).text.strip()
import re

price_num = re.findall(r"￥(\d+)", price)[0]
comment_num = re.findall(r"已有(\d+)人评价", comment)[0]

print(title)
print(price, price_num)
print(comment, comment_num)
print("-" * 30)

案例：双色球历史数据
第1页：HTML格式
import requests
from bs4 import BeautifulSoup

res = requests.get(
url="https://m.78500.cn/kaijiang/ssq/",
headers={
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
}
)

soup = BeautifulSoup(res.text, features="html.parser")

parent_area = soup.find(name="article", attrs={'id': "list"})

section_list = parent_area.find_all(name='section', attrs={"class": "item"})
for section in section_list:
title = section.find(name="strong").text
code = section.find(name="p").text

print(title, code)

第2+页：JSON格式
import requests
from bs4 import BeautifulSoup

res = requests.get(
url="https://m.78500.cn/kaijiang/ssq/",
headers={
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
}
)

cookie_dict = res.cookies.get_dict()

print(cookie_dict)

soup = BeautifulSoup(res.text, features="html.parser")

parent_area = soup.find(name="article", attrs={'id': "list"})

section_list = parent_area.find_all(name='section', attrs={"class": "item"})
for section in section_list:
title = section.find(name="strong").text
code = section.find(name="p").text
print(title, code)

第2页（请求与网页不一致）

for i in range(1, 11):
res = requests.get(
url=f"https://m.78500.cn/kaijiang/ssq/?years=list&page={i}",
headers={
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
"Accept": "application/json"
},
cookies=cookie_dict
)
data_dict = res.json()
for row in data_dict['list']:
# print(row['qishu'], "".join(row['result']))
line = f"{row['qishu']}期 {''.join(row['result'])}"
print(line)

标签：re,Python,text,day07,武沛齐,path,print,import,os
From： https://www.cnblogs.com/fresher20240311/p/18067184