xiaoouwang

xiaoouwang

xiaoouwang

xiaoouwang

xiaoouwang

# Author: Xiaoou Wang [linkedin](https://www.linkedin.com/in/xiaoou-wang)/[email](mailto:xiaoouwangfrance@gmail.com)
# https://xiaoouwang.medium.com/complete-tutorial-on-scraping-french-news-from-le-monde-%EF%B8%8F-4fa92bc0a07b 
# Have a look at https://soshace.com/responsible-web-scraping-gathering-data-ethically-and-legally/ before using the code.
import os  # helper functions like check file exists
import datetime  # automatic file name
import requests  # the following imports are common web scraping bundle
from urllib.request import urlopen  # standard python module
from bs4 import BeautifulSoup
from urllib.error import HTTPError
from collections import defaultdict

xiaoouwang

xiaoouwang

xiaoouwang

xiaoouwang

# https://xiaoouwang.medium.com/comprendre-la-m%C3%A9thode-str-en-python-et-lavantage-de-repr-d40fceb833a1
# Author: Xiaoou Wang, Master's student in natural language processing looking for a phd position/contrat cifre. https://www.linkedin.com/in/xiaoou-wang/
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age


p1 = Person("John", 36)
print(p1)  # <__main__.Animal object at 0x7f9060250410>

xiaoouwang

# Author: Xiaoou Wang, Master’s student in natural language processing looking for a phd position/contrat cifre. 
# https://xiaoouwang.medium.com/get-readable-bash-command-history-with-cut-and-vscode-4eb8d56f38b4
history | tail -n 15 # show the last 15 commands
echo "abcdefghi" | cut -c2-6 # extract the 2nd to the 6th character 
# output = bcdef
echo "a-b-c" | cut -d'-' -f2 # split the string into 3 parts and get the 2nd part
# output = b
history | cut -d' ' -f4- | tail -n 15 # separate using space, get the 4th to nth column, get the last 15 commands
history | cut -d' ' -f4- | tail -n 15 | code - # show the results in vsc
history | grep “python” | cut -d' ' -f 4- | tail -n 15 | code - # Seach a command containing specific string