def get_js(js, js_fun, js_params):
try:
import execjs # pip install PyExecJS
except:
raise LibraryNotInstallError('安装：pip install PyExecJS')
ctx = execjs.compile(js) # 加载JS文件
return ctx.call(js_fun, *js_params) # 调用js方法 第一个参数是JS的方法名，后面的data和key是js方法的参数
def analysis(data_name, response_headers=Response_Headers):
"""分析单词、爬去小D网站：https://dict.hjenglish.com/jp/jc/%E3%81%AB%E3%81%8E%E3%82%8F%E3%81%86"""
try:
from bs4 import BeautifulSoup # pip install bs4
except Exception as _:
raise LibraryNotInstallError('安装 pip install bs4')
total = []
ws = open(data_name + '.data', 'w', encoding='utf8')
with open(data_name, encoding='utf8') as f:
for line in f:
lines = line[:-1]
if len(lines) > 1 and (lines not in total):
total.append(lines)
name = lines
url = F'https://dict.hjenglish.com/jp/jc/{quote(name)}'
response = requests.get(
url=url, headers=jtyoui.header(response_headers))
data = response.text
sp = BeautifulSoup(data, 'html.parser')
pjm = sp.find(class_='pronounces')
if pjm:
pjm = pjm.span.text[1:-1]
else:
continue
cx = sp.find(class_='simple')
x = cx.h2
if x:
x = x.text[1:-1]
else:
continue
m = cx.ul.text.replace('\n', '')
m = sub_names(m).replace('。', '；')[:-1]
if len(m) > 40:
continue
if name != pjm:
name = "(" + name + ")"
else:
name = None
x = '<' + x + '>'
for k, v in word.items():
x = x.replace(k, v)
x = x.replace('词', '')
if len(m) <= 1:
continue
if name:
string = F'{pjm}{name}\t{x}\t{m}'
else:
string = F'{pjm}\t{x}\t{m}'
print(string)
ws.write(string + '\n')
ws.flush()
def cut(text_name):
"""从原始数据里面提取日语单词
:param text_name:原始数据的文件地址
:return:返回提取数据文本的地址
"""
try:
from janome.tokenizer import Tokenizer # pip install janome
except Exception as _:
raise LibraryNotInstallError('安装 pip install janome')
w = open(text_name + '.jp', 'w', encoding='utf8')
t = Tokenizer()
fp = open(text_name, encoding='utf-8')
for token in t.tokenize(fp.read()):
words = token.base_form
words = words.replace(' ', '')
if len(words) > 1:
w.write(words + '\n')
return text_name + '.jp'
# @Email : [email protected] # @Software: PyCharm from jtyoui.error import LibraryNotInstallError from jtyoui.tools import pips import os import glob import zipfile import shutil try: import fitz # 安装 pip install PyMuPDF except ModuleNotFoundError: try: fitz = pips('fitz', 'PyMuPDF') # 自动安装 except ModuleNotFoundError: raise LibraryNotInstallError("安装 pip install PyMuPDF") def _get_dir_name(file_dir): base_name = os.path.basename(file_dir) # 获得地址的文件名 dir_name = os.path.dirname(file_dir) # 获得地址的父链接 return dir_name, base_name def image_pdf(file_dir, pdf_address=None): """ 照片转pdf :param file_dir: 照片的地址文件夹 :param pdf_address: 保存pdf的文件地址，默认是当前地址 :return: 成功返回True """
#!/usr/bin/python3.7 # -*- coding: utf-8 -*- # @Time : 2019/2/14 0014 # @Email : [email protected] import requests from jtyoui.web import random from jtyoui.error import LibraryNotInstallError import re try: import itchat # 安装 pip install itchat except ModuleNotFoundError: raise LibraryNotInstallError("安装 pip install itchat") url = 'https://m.xunleige.com/' def movie(name): param = dict(searchword=name.encode('gb2312')) response = requests.post(url + 'search.asp', data=param, headers={'User-Agent': random()}) response.encoding = 'GBK' data = response.text find, = re.findall(pattern=r'<div class="list mb">(.+)</div>', string=data, flags=re.S) message = re.findall(pattern='a href="(.+)" title="(.+)" class', string=find) return message
# -*- coding: utf-8 -*- # @Time : 2018/1/2 16:30 # @Email : [email protected] # @Software: PyCharm import random import sys import time from jtyoui.error import LibraryNotInstallError from urllib.request import urlretrieve import os try: import pygame except ModuleNotFoundError: raise LibraryNotInstallError("安装pygame包: pip install pygame") SCREEN_WIDTH, SCREEN_HEIGHT = 1200, 700 MY_BIRTH_LEFT, MY_BIRTH_TOP = SCREEN_WIDTH / 2, SCREEN_HEIGHT - 60 DIRECTION = [U, D, L, R] = ['U', 'D', 'L', 'R'] Tank_IMAGE_POSITION = './tank_img' URL = 'https://gitee.com/tyoui/logo/raw/master/img/' def load_img(name_img): save = Tank_IMAGE_POSITION + os.sep + name_img + '.gif' if not os.path.exists(save): urlretrieve(URL + name_img + '.gif', save) return pygame.image.load(save)