# For parsing and creating soup objects
import os
fileSaveDir = os.chdir(
'/Users/ChrisErnst/Development/data-science-lessons-di/Seventeenth_Lesson')
# Set the directory
from utilities import add_link, email_client
# import our link adding function
import numpy as np
# good ol numpy (for matrix and array manipulation)
import pandas as pd
# for exporting to csv
linkList = []
# Create an empty list we will use to hold links
linkList.append(add_link(2001, model='accord'))
linkList.append(add_link(2000))
# build our list of urls to specific desired models
page = requests.get(linkList[1])
# Sets page to the target URL
chaos = page.text # requests function
# Makes the html a text-based object
soup = BeautifulSoup(chaos, 'html.parser')
# Uses a html parser to break up the html blocks
newBlockLong = soup.find_all('p', 'result-info')
# Returns a result set
type(newBlockLong)
# Build the linklist with the input data year and model for all counties
linkList = []
# Build an optional linkList for link debugging later on
# import webbrowser as wb # debugging
# Make a request for each of the links, and add it to list ourResultMatrix
ourResultMatrix = []
for j in range(len(inputData)):
tempYear = inputData['year'][j]
tempModel = inputData['model'][j]
print("\nWorking on", tempYear, tempModel, "| Vehicle ", j + 1, " of",
len(inputData), "\n")
links = add_link(tempYear, model=tempModel)
# for f in range(len(links)):
linkList.append(links)
for x in range(len(links)):
print("\nWorking on link:", x + 1, "of", len(links), "\n")
page = requests.get(links[x])
# Sets page to the target URL
chaos = page.text # requests function
# Makes the html a text-based object
soup = BeautifulSoup(chaos, 'html.parser')
'/Users/ChrisErnst/Development/data-science-lessons-di/Seventeenth_Lesson')
# Set the directory
from utilities import add_link
from utilities import email_client
# import our link adding function
import numpy as np
# good ol numpy (for matrix and array manipulation)
import pandas as pd
# for exporting to csv
from datetime import datetime
import time
linkList = []
# Create an empty list we will use to hold links
linkList.append(add_link(2001, model='accord')) # 0th element
linkList.append(add_link(2000)) # 1st element
# build our list of urls to specific desired models
page = requests.get(linkList[1])
# Sets page to the target URL
chaos = page.text # requests function
# Makes the html a text-based object
soup = BeautifulSoup(chaos, 'html.parser')
# Uses a html parser to break up the html blocks
newBlockLong = soup.find_all('p', 'result-info')
# Returns a result set
type(newBlockLong)