python 常用方法笔记

import requests
from bs4 import BeautifulSoup


headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36",
    "Cookie": ""
}   # 请求头


def request(url):
    req = requests.get(
        url,
        headers=headers)
    try:
        types = req.apparent_encoding
        req.encoding = types
    except:
        None
    html = req.text
    meta = BeautifulSoup(html, 'html.parser')
    return meta

url = "www.baidu.com" 
meta = request(url)  

# 标签获取数据
text = meta.select('div[id="content"]')[0].text 

# 经常使用的两个正则
re.sub("\xa0\xa0\xa0\xa0", "", text)      
re.findall('(.*)', text)[0]



with open(paths, encoding="utf-8") as f:  # 读取文件数据
    text = f.read()
    f.close()



from xlutils.copy import copy
import xlrd  # pip install xlrd==1.2.0
def write_excel_xlsx_append(value, path):
    '''
    :param value:  [a,a,a,a,a]
    :return:
    '''
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    rows_old = worksheet.nrows  # 获取表格中已存在的数据的行数
    new_workbook = copy(workbook)  # 将xlrd对象拷贝转化为xlwt对象
    new_worksheet = new_workbook.get_sheet(0)  # 获取转化后工作簿中的第一个表格
    for i in range(index):
        new_worksheet.write(rows_old, i, value[i])  # 追加写入数据，注意是从rows_old行开始写入
    new_workbook.save(path)  # 保存工作簿
    print("写入数据成功！")


def write_excel_xlsx_append_MAX(value, path):
    '''
    :param value:  [[a,a,a,a,a], [b,b,b,b]]
    :return:
    '''
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    rows_old = worksheet.nrows  # 获取表格中已存在的数据的行数
    new_workbook = copy(workbook)  # 将xlrd对象拷贝转化为xlwt对象
    new_worksheet = new_workbook.get_sheet(0)  # 获取转化后工作簿中的第一个表格
    for i in range(0, index):
        for j in range(0, len(value[i])):
            new_worksheet.write(i + rows_old, j, value[i][j])  # 追加写入数据，注意是从i+rows_old行开始写入
    new_workbook.save(path)  # 保存工作簿
    print("写入数据成功！")


def open_workbook(paths, hang):
    '''
    读取一列数据
    '''
    data = xlrd.open_workbook(paths)  # 读取文件
    sheets = data.sheet_by_index(0).col_values(hang)
    return sheets


import pandas as pd
def dq_xls(path):
    ''' 表格读取都可以用
    :param path:
    :return:[[a,a,a],[a,a,a],[a,a,a]]
    '''
    dr_data = pd.read_excel(path)
    dr_data = dr_data.fillna("")
    dr_list = dr_data.values.tolist()
    return dr_list

def dq_xls(path, sheet_name):
    ''' 表格读取都可以用
    读取指定sheet数据
    :param path:
    :return:[[a,a,a],[a,a,a],[a,a,a]]
    '''
    dr_data = pd.read_excel(path, sheet_name=sheet_name)
    dr_data = dr_data.fillna("")
    dr_list = dr_data.values.tolist()
    return dr_list
def new_xlsx(path):
    work_book = xlwt.Workbook(encoding='utf-8')
    sheet = work_book.add_sheet('sheet')
    work_book.save(path)


dir = os.path.abspath('media') # 获取文件夹名路径

dir = os.path.dirname(__file__) # 获取当前路径

    
'''
        判断目录是否存在，如果不存在创建目录
'''
pd = os.path.exists(path)
if not pd:
    os.makedirs(path)


data_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()))
data_time = time.strftime("%Y-%m-%d", time.localtime(time.time() - 86400))

import time
from datetime import datetime
st = '2022-09-16 11:03:35'
time_str = time.mktime(datetime.strptime(st, '%Y-%m-%d %H:%M:%S').timetuple())


def untar_win(fname, dirs):
    """
    解压tar.gz文件
    :param fname: 压缩文件名s
    :param dirs: 解压后的存放路径
    :return: bool
    """
    try:
        t = tarfile.open(fname)
        t.extractall(path=dirs)
        return True
    except Exception as e:
        print(e)
        return False


# 输入
import win32api
import win32con
import ctypes
def input_str(data_str):
    for i in str(data_str):
        MapVirtualKey = ctypes.windll.user32.MapVirtualKeyA
        an = ord(i)
        win32api.keybd_event(an, MapVirtualKey(an, 0), 0, 0)  
        win32api.keybd_event(an, MapVirtualKey(an, 0), win32con.KEYEVENTF_KEYUP, 0)

# 点击
from pynput.mouse import *
def dianji(x, y):
    m = Controller()
    m.position = (x, y)
    print('设置鼠标的坐标:{0}'.format(m.position))
    time.sleep(1)
    # m.move(m.position[0], m.position[1])
    m.press(Button.left)
    m.release(Button.left)
    time.sleep(1)


# 开进程
from multiprocessing import Process
p = Process(target=you_def, args=(file_data_one,))
p.start()

# 验证码
import ddddocr
ocr = ddddocr.DdddOcr()
with open('1.jpg', 'rb') as f:
    img_bytes = f.read()
res = ocr.classification(img_bytes)

import ddddocr


def get_ddddocr(path):
    ocr = ddddocr.DdddOcr()
    with open(path, 'rb') as f:
        img_bytes = f.read()
    res = ocr.classification(img_bytes)
    return res

# 图片识别
import pytesseract
from PIL import Image

image = Image.open('2.jpg')
t = pytesseract.image_to_string(image, lang='chi_sim')

# 图片截取
from PIL import Image
def img_jq(data):
    '''
      图片截取
    date = {
        'x': '474',
        'y': '407',
        'w': '964',
        'h': '38',
        'path': '1.jpg',
        'out_name_path': 'test2.jpg',
    }
    :param data:
    :return:
    '''
    path = data['path']
    x = float(data['x'])
    y = float(data['y'])
    w = float(data['w'])
    h = float(data['h'])
    out_name_path = data['out_name_path']
    im = Image.open(path)
    region = im.crop((x, y, x + w, y + h))
    region = region.convert('RGB')
    region.save(out_name_path)


# 字符串转json
json3=ast.literal_eval(str)


# chromedriver使用
# http://chromedriver.storage.googleapis.com/index.html
from selenium import webdriver
url = 'www.baidu.com'
chrome_options = webdriver.ChromeOptions()
chromedriver_path = r'chromedriver.exe'
# chrome_options.add_argument("--auto-open-devtools-for-tabs")
# chrome_options.add_argument('--start-maximized')
# chrome_options.add_argument('--headless')
chrome_options.add_argument("--window-size=1920,1080")
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument(
    '--user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"')
brow = webdriver.Chrome(executable_path=chromedriver_path, options=chrome_options)
brow.set_page_load_timeout(8)
brow.get(url)
brow.execute_script('window.stop()')
brow.find_element_by_id("txtUserName2").click()
brow.find_element_by_id("txtUserName2").send_keys(user)

# 切换内置网页
iframe = brow.find_element_by_css_selector('iframe')
print(iframe)
brow.switch_to_frame(iframe)