generate functionThu, 11 May 2023
read a txt file into a list ,igno ENTER
def readlist(file_name):
with open(file_name,'r') as f:
lst = [i.strip().split(',') for i in f.readlines()]
return lst
readlist('f.txt')
Python
ViewAll generations.
generate functionTue, 02 May 2023
Extracting text from HTML file
import urllib.request
from bs4 import BeautifulSoup
url = "https://en.wikipedia.org/wiki/List_of_state_and_union_territory_capitals_in_India"
html = urllib.request.urlopen(url)
soup = BeautifulSoup(html, 'html.parser')
for tr in soup.find_all('table'):
for td in tr.find_all('td'):
text = td.find(text=True)
print(text)
Python
Viewgenerate functionTue, 02 May 2023
read a html file
def read_html():
with open('my.html') as f:
return f.read()
html = read_html()
Python
Viewgenerate functionTue, 23 May 2023
find out all the Chinese characters
def isChinese(word):
if u'\u4e00' <= word <= u'\u9fff':
return True
else:
return False
isChinese('人')
Python
Viewgenerate functionWed, 10 May 2023
Find out the elements that hided in the html file
def find_element(filename):
with open(filename) as file:
tree = html.fromstring(file.read())
return tree.xpath('//li/a/@href')
find_element('sample.html')
Python
Viewgenerate functionThu, 25 May 2023
Judge whether the character is in simplified japanese characters
def is_japanese(char):
return 0x4e00 <= ord(char) <= 0x9fff
is_japanese("日")
Python
Viewgenerate functionThu, 25 May 2023
Identify all of the Chinese characters
import re
def chinese_char(string):
match = re.search(u'[\u4e00-\u9fff]+', string)
if match != None:
return True
else:
return False
Python
Viewgenerate functionFri, 12 May 2023
Find all the Chinese characters in a file mixed with Chinese, Japanese and English using langid
def find_chinese(filename):
text = open(filename, "r").read()
text = re.sub("[\s+\.\!\/_,$%^*(+\"\'“”《》?“]+|[+——！，。？、~@#￥%……&*（）]+", "",text)
result = ""
for i in text:
if langid.classify(i)[0]=="zh":
result += i
return result
Python
Viewgenerate functionThu, 11 May 2023
read a txt file into a list and replace \n to space
def readIntoList():
with open('C:\Users\xxx\Desktop\xxx\xxx.txt','r') as f:
li = []
line = f.readline()
while line:
#print(line)
line = line.replace('\n','')
line = line.replace(' ',' ')
line = line.replace(' ',' ')
li.append(line)
line = f.readline()
f.close()
return li
Python
Viewgenerate functionFri, 28 Apr 2023
Export all of the japan characters in the html file into a text file
import codecs
with codecs.open('kantai_collection.html', 'r', 'utf-8') as f:
data = f.read()
with codecs.open('kantai_collection.txt', 'w', 'utf-8') as f2:
for x in data.split('<p>')[1:]:
f2.write(x.split('</p>')[0] + '\n')
Python
Viewgenerate functionTue, 23 May 2023
Determine whether the character is Japanese or not
def is_japanese(s):
if s >= u'\u4e00' and s <= u'\u9faf':
return True
else:
return False
is_japanese(u'涼太')
Python
Viewgenerate functionTue, 02 May 2023
Export all of the japan characters in the html file into a text file
function(htmlFile) {
//TODO
}
Javascript
Viewgenerate functionWed, 03 May 2023
read a html file and Extract all of the japanese
import re
from bs4 import BeautifulSoup
def get_japanese(html_file):
soup = BeautifulSoup(open(html_file), 'html.parser')
japanese = soup.findAll(text=re.compile(".*[\u4E00-\u9FFF]+.*"))
return japanese
get_japanese("test.html")
Python
Viewgenerate functionWed, 03 May 2023
read all of the .html files which in afolder
import glob
for file in glob.glob("*.html"):
print(file)
Python
Viewgenerate functionThu, 11 May 2023
delete all of the world that in a list from a txt file
def delete_words(words, filename):
f = open(filename,'r')
lines = f.readlines()
for line in lines:
for word in words:
line = line.replace(word,'')
print(line)
f.close()
Python
Viewgenerate functionWed, 10 May 2023
Find out the elements that hide in the html file
titles = tree.xpath("//div[@class='course-card-container']//h3/text()")
Python
Viewgenerate functionFri, 28 Apr 2023
Find all the Japanese characters in the html file
import re
def find_japanese(file):
japanese_regex = re.compile(r'[\u3000-\u303f\u3040-\u309f\u30a0-\u30ff\uff00-\uff9f\u4e00-\u9faf\u3400-\u4dbf]')
text = open(file)
text = text.read()
text = text.strip().split()
japanese = []
for i in text:
if japanese_regex.search(i):
japanese.append(i)
return japanese
find_japanese('html_file.txt')
Python
Viewgenerate functionFri, 12 May 2023
read out off the word in the image
def image_to_string(img):
return (img.split("_")[1]).split(".")[0]
image_to_string(image_list[0])
Python
Viewgenerate functionThu, 20 Apr 2023
compare alots of number in a list, pickup the greast number
// function that: compare alots of number in a list, pickup the greast number
function findGreatestNum(numbers){
let greatestNum = numbers[0];
for (let num of numbers){
if (num > greatestNum){
greatestNum = num;
}
}
return greatestNum;
}
console.log(findGreatestNum([3,4,5,6,7,8,9,10]));
TypeScript
Viewgenerate functionMon, 17 Apr 2023
compare many number in a list, pickup the greast number
Script
function greast(numbers){
if(numbers.length === 0){
return 0
}
var max = numbers[0]
for(var i = 1; i < numbers.length; i++){
if(numbers[i] > max){
max = numbers[i]
}
}
return max
}
greast([2, 3, 1, 4, 5, 6, 7])
Java
Viewgenerate functionTue, 18 Apr 2023
compare many number in a list, pickup the greast number
const compareNumbers = (a, b) => {
if (a > b) {
return a;
} else if (a < b) {
return b;
} else {
return `${a} = ${b}`;
}
}
compareNumbers(1, 2)
TypeScript
Viewgenerate functionTue, 02 May 2023
use BeautifulSoup import a html file
from bs4 import BeautifulSoup
import urllib.request
def get_soup(url):
page = urllib.request.urlopen(url).read()
soup = BeautifulSoup(page, "html.parser")
return soup
soup = get_soup("https://www.pythonforbeginners.com/beautifulsoup/beautifulsoup-4-python")
Python
Viewgenerate functionTue, 02 May 2023
Extracting text from HTML file
from bs4 import BeautifulSoup
with open('html_file.html') as file:
soup = BeautifulSoup(file.read())
text = soup.get_text()
Python
Viewgenerate functionFri, 14 Apr 2023
connect the db2 database
def connect():
conn = ibm_db.connect(dsn, "", "")
return conn
Python
Viewgenerate functionFri, 28 Apr 2023
Export all of the Japanese characters in a html file to a text file
from bs4 import BeautifulSoup
import requests
import re
r = requests.get('http://www.aozora.gr.jp/cards/000148/files/773_14547.html')
soup = BeautifulSoup(r.content, 'lxml')
def get_text(soup):
text_list = []
for text in soup.find_all('p'):
text_list.append(text.get_text())
return text_list
with open('text.txt', 'w') as f:
for text in get_text(soup):
f.write(text + '\n')
Python
Viewgenerate functionFri, 14 Apr 2023
Click the target useing the text in the screen
# Use the text in the screen to click the target
def clickWithText(text):
if exists(text):
click(text)
else:
exit(1)
clickWithText("Next")
Python
Viewgenerate functionFri, 14 Apr 2023
Click the taget with text in the screen
def baidu_search(text):
driver.find_element_by_id("kw").send_keys(text)
driver.find_element_by_id("su").click()
baidu_search("Hao")
Python
Viewgenerate functionWed, 03 May 2023
read a html file and Extract all of the japanese kannji hiragana katagana
from bs4 import BeautifulSoup
def read_html(file):
with open(file) as f:
soup = BeautifulSoup(f, 'lxml')
return soup.find_all(class_='jp')
read_html('japanese.html')
Python
Viewgenerate functionWed, 03 May 2023
write a file line by line
with open('/Users/user/myfile.txt', 'w') as file:
for i in range(1, 11):
file.write('{}\n'.format(i))
Python
Viewgenerate functionTue, 18 Apr 2023
compare alots of number in a list, pickup the greast number
function greatest(numbers) {
let greatest = 0;
numbers.forEach(function (n) {
if (n > greatest) {
greatest = n;
}
});
return greatest;
}
greatest([1, 2, 34, 5, 6, 7, 9, 10])
TypeScript
Viewgenerate functionFri, 14 Apr 2023
Click the taget with text in the screen
clickElementWithText("text");
Java
Viewgenerate functionFri, 12 May 2023
read out off the word in the png file
def read_image(image_file):
'''
this function takes in an image file and outputs the text contained in the file.
'''
text = image_file
return text
Python
Viewgenerate functionWed, 24 May 2023
Judge whether the character is a simplified Chinese character
def is_chinese(uchar):
if '\u4e00' <= uchar<='\u9fff':
return True
else:
return False
Python
Viewgenerate functionFri, 12 May 2023
Find all the Chinese characters in a file mixed with Chinese, Japanese and English
# coding: UTF-8
import re
def find_chinese_characters(file_path):
with open(file_path, 'r') as file:
text = file.read()
pattern = re.compile(u'[\u4e00-\u9fff]+')
result = pattern.findall(text)
return result
print(find_chinese_characters('text.txt'))
Python
Viewgenerate functionThu, 25 May 2023
Judge whether the character is japanese characters
def is_japanese_character(character):
return 0x4E00 <= ord(character) <= 0x9FFF
is_japanese_character("中")
Python
Viewgenerate functionFri, 28 Apr 2023
Export all of the Japanese characters in the html file into a text file
from bs4 import BeautifulSoup
import re
from urllib.request import urlopen
def export(url):
soup = BeautifulSoup(urlopen(url), 'html.parser')
japanese_characters = soup.find_all('div', {'class': 'text'})
with open('japanese.txt', 'w') as f:
for x in japanese_characters:
f.write(x.get_text())
f.write('\n\n')
Python
Viewgenerate functionWed, 03 May 2023
read all of the .html files which in a folder
def read_html(folder):
for filename in os.listdir(folder):
if filename.endswith(".html"):
infile = folder + filename
with open(infile, "r") as f:
text = f.read()
print(text)
Python
Viewgenerate functionTue, 02 May 2023
use BeautifulSoup read a html file
import beautifulsoup4
def read_html(file):
f = open(file)
html = f.read()
soup = BeautifulSoup(html, 'html.parser')
return soup
read_html("test.html")
Python
Viewgenerate functionWed, 10 May 2023
Find out the elements css style in the html file
import selenium.webdriver
driver = selenium.webdriver.Chrome()
driver.get('https://www.python.org/')
element = driver.find_element_by_class_name('search-field')
element.get_attribute('style')
Python
Viewgenerate functionThu, 25 May 2023
Judge whether the character is in simplified Chinese characters
def is_chinese(uchar):
# is_chinese('一') = True
# is_chinese('A') = False
if u'\u4e00' <= uchar <= u'\u9fff':
return True
else:
return False
Python
Viewgenerate functionWed, 03 May 2023
read all the html files in the folder
import os
def read_files(path):
file_list = os.listdir(path)
return file_list
read_files('./')
Python
Viewgenerate functionTue, 02 May 2023
Export all of the japan characters in the html file into a text file
const fs = require('fs');
const path = require('path');
const html = fs.readFileSync(path.join(__dirname, 'japan.html'), 'utf8');
const puppeteer = require('puppeteer');
const cheerio = require('cheerio');
const $ = cheerio.load(html);
const japanCharCodes = [0x3040, 0x3097];
const japanChars = [];
japanCharCodes.forEach(japanCharCode => {
for (let i = 0; i < 96; i++) {
japanChars.push(String.fromCodePoint(japanCharCode + i));
}
});
const browser = await puppeteer.launch({
headless: false,
});
const page = await browser.newPage();
await page.goto('http://www.rikai.com/library/kanjitables/kanji_codes.unicode.shtml');
await page.on('console', async msg => {
TypeScript
Viewgenerate functionWed, 10 May 2023
Find out the elements that are not displayed in the html file
def get_missing_elements(driver):
web_elements = driver.find_elements_by_xpath("//*")
html_elements = driver.page_source
for element in web_elements:
html_elements = html_elements.replace(element.get_attribute('outerHTML'), '')
print(html_elements)
return html_elements
Python
Viewgenerate functionThu, 11 May 2023
delete all of the world that in a list from a txt file read with utf8
def delete_words(words, file):
f = open(file, 'r', encoding='utf8')
for line in f.readlines():
for word in words:
line = line.replace(word, '')
f1 = open(file, 'a', encoding='utf8')
f1.write(line)
f.close()
Python
Viewgenerate functionWed, 03 May 2023
output a file line by line
def echo_file(fname):
with open(fname) as f:
for line in f:
print(line)
echo_file('path/to/file')
Python
View