poa00

import asyncio
import os
import winrt

from PIL import Image
from winrt.windows.graphics.imaging import BitmapDecoder, BitmapPixelFormat, SoftwareBitmap
from winrt.windows.media.ocr import OcrEngine
from winrt.windows.storage import StorageFile, FileAccessMode
import winrt.windows.storage.streams as streams

poa00

import urllib

def crawler(seedurl,max_depth):
    tocrawl=[seedurl]
    crawled=[]
    index={}
    graph={}
    while tocrawl:
        url=tocrawl.pop()
        if url not in crawled and len(crawled)<=max_depth:

poa00

poa00

#scraper for http://www.adafruit.com/
from BeautifulSoup import *
#from nextpage import *
import urllib
import MySQLdb
#library to take care of the unicode problem
#More info here : http://stackoverflow.com/a/1207479
import unicodedata

db=MySQLdb.connect("127.0.0.1","root","","adafruit_products" )

poa00

from locale import currency
from freelancersdk.resources.projects import place_project_bid
from freelancersdk.session import Session
from freelancersdk.resources.users \
    import get_self_user_id
from freelancersdk.resources.projects.projects import (
    get_projects, get_project_by_id
)
from freelancersdk.resources.projects.helpers import (
    create_get_projects_object, create_get_projects_project_details_object,

poa00

poa00

df = pd.DataFrame(list(zip([None if x == None else x.string for x in soup.find_all('h3')],
                           [None if x.find(attrs={'class':'price_color'}) == None else x.find(attrs={'class':'price_color'}).string.replace('£','') for x in soup.find_all(attrs={'class':'col-xs-6 col-sm-4 col-md-3 col-lg-3'})],
                           [None if x.find(attrs={'class':'instock availability'}).text == None else x.find(attrs={'class':'instock availability'}).text.strip() for x in soup.find_all(attrs={'class':'col-xs-6 col-sm-4 col-md-3 col-lg-3'})],
                           [None if x.find(attrs={'class':re.compile(r'star-rating$')}).get('class') == None else x.find(attrs={'class':re.compile(r'star-rating$')}).get('class')[1] for x in soup.find_all(attrs={'class':'col-xs-6 col-sm-4 col-md-3 col-lg-3'})])),
                  columns=['product_name','price','availability','rating'])

poa00

import pandas as pd
from selenium import webdriver
from bs4 import BeautifulSoup
import re
import requests
import time

url = 'https://books.toscrape.com/catalogue/page-1.html'
driver = webdriver.Chrome()
driver.implicitly_wait(30)

poa00

Remove 'Copy of' prefix from Google Drive filenames

xterm is a nifty Unix console emulator you can use in Google Colab notebooks. We can use it to manipulate files hosted on Google Drive in batch

step 1: mount your Drive in Colab

Paste the following code in a 'code' cell of the Colab notebook and click Run

from google.colab import drive

poa00

from splinter import Browser
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup as bs
import pandas as pd
import requests
import os
import time