Develop Reference

Python to excel

I created a script to pull data from a website and paste it in excel. The script works, however when I extract the Name from the website and it paste in excel for some reason its very small. But when you click in the cell its normal size. See image here.
I tried to show a snip it as an example but stack won't allow me.
Here is the current code
from openpyxl import load_workbook
from bs4 import BeautifulSoup
import requests
# Fetch the HTML page
url = 'https://esearch.mobilecopropertytax.com/Property/View/466089'
response = requests.get(url)
html = response.text
# Parse the HTML page
soup = BeautifulSoup(html, 'lxml')
# Find the element containing the Parcel Number
element = soup.find('th', text='Parcel Number:')
# Extract the Parcel Number from the element
parcel_number = element.find_next_sibling().text
# Find the element containing the Name
element = soup.find('th', text='Name:')
# Extract the Name from the element
name = element.find_next_sibling().text
# Load the workbook
wb = load_workbook(r'C:\Users\user\EJW Test\EJWtest.xlsx')
# Select the sheet
ws = wb['Justification Worksheet']
# Select the cells
cell1 = ws['C7'] # Parcel Number
cell2 = ws['C10'] # Name
# Set the values of the cells
cell1.value = parcel_number
cell2.value = name
# Save the workbook
wb.save('completetest.xlsx')
Unsure why it puts the parcel info in just fine but inserts the name into excel and it looks completely different.

Extract Text into Column using Regex

I want to extract data (S no, Item Code, Price and Size) from the attached PDF Document in to columns.
The re.compile works for the S no, Item Code and Price, but as soon as I put the Size - it gives a limited output. I am unable to figure out why? Can you please help
(Attached picture of the PDF page)
Import pandas as pd
Import re
Import PyPDF2
file = open("Petchem.pdf", "rb")
pdfReader = PyPDF2.PdfFileReader(file)
my_dict = {"S no":[], "Item Code":[], "Price":[], "Size":[]}
for page in range (1,25):
pageObj = pdfReader.getPage(page)
data = pageObj.extractText()
size = re.compile(r'((\d{2,4}?)(\d{10})EA\s(\d?\d?,?\d?\d?\d.\d\d)[\s\w\d,:/.()-])')
for number in size.findall(data):
S_No = my_dict["S No"].append(number[1])
Item_Code = my_dict["Item Code"].append(number[2])
Price = my_dict["Price"].append(number[3])
Size = my_dict["Size"].append(number[4])
print(number[1])
a_file = open("Column_Breakup.csv", "w")
datadf = pd.DataFrame(my_dict)
datadf.to_csv("Column_Breakup.csv")
a_file.close()

Unable to convert multiple PDF pages of a PDF File into a CSV using tabula

I have PDF file whose 1st page data format is different however rest of the pages has the same tabular format.
I want to convert this PDF file which has multiple pages into a CSV file using Python Tabula.
The current code is able to convert PDF to CSV if the PDF has only 2 pages and if it has more that two pages it gives error out of range.
I want to count total number of PDF pages of a PDF File and depending upon the same I want python script to convert the PDF to CSV for different data frames.
I am using Linux box to run this python script.
The code is as given below:
#!/usr/bin/env python3
import tabula
import pandas as pd
import csv
pdf_file='/root/scripts/pdf2xls/Test/21KJAZP011.pdf'
column_names=['Product','Batch No','Machin No','Time','Date','Drum/Bag No','Tare Wt.kg','Gross Wt.kg',
'Net Wt.kg','Blender','Remarks','Operator']
df_results=[] # store results in a list
# Page 1 processing
try:
df1 = tabula.read_pdf('/root/scripts/pdf2xls/Test/21KJAZP011.pdf', pages=1,area=(95,20, 800, 840),columns=[93,180,220,252,310,315,333,367,
410,450,480,520]
,pandas_options={'header': None}) #(top,left,bottom,right)
df1[0]=df1[0].drop(columns=5)
df1[0].columns=column_names
df_results.append(df1[0])
df1[0].head(2)
except Exception as e:
print(f"Exception page not found {e}")
# Page 2 processing
try:
df2 = tabula.read_pdf('/root/scripts/pdf2xls/Test/21KJAZP011.pdf', pages=2,area=(10,20, 800, 840),columns=[93,180,220,252,310,315,330,370,
410,450,480,520]
,pandas_options={'header': None}) #(top,left,bottom,right)
row_with_Sta = df2[0][df2[0][0] == 'Sta'].index.tolist()[0]
df2[0] = df2[0].iloc[:row_with_Sta]
df2[0]=df2[0].drop(columns=5)
df2[0].columns=column_names
df_results.append(df2[0])
df2[0].head(2)
except Exception as e:
print(f"Exception page not found {e}")
#res:wult = pd.concat([df1[0],df2[0],df3[0]]) # concate both the pages and then write to CSV
result = pd.concat(df_results) # concate list of pages and then write to CSV
result.to_csv("result.csv")
with open('/root/scripts/pdf2xls/Test/result.csv', 'r') as f_input, open('/root/scripts/pdf2xls/Test/FinalOutput_21KJAZP011.csv', 'w') as f_output:
csv_input = csv.reader(f_input)
csv_output = csv.writer(f_output)
csv_output.writerow(next(csv_input)) # write header
for cols in csv_input:
for i in range(7, 9):
cols[i] = '{:.2f}'.format(float(cols[i]))
csv_output.writerow(cols)
Please suggest how can achieve the same. I am very new to Python and hence unable to put together things.

Try pdfpumber https://github.com/jsvine/pdfplumber, worked for me like a charm
pdffile = 'your file'
with pdfplumber.open(pdffile) as pdf:
for i in range(len(pdf.pages)):
first_page = pdf.pages[i]
rawdata = first_page.extract_table()

Extract Multiple Tables from PDF using multiple_tables options using tabula
multiple_tables=True
from tabula import convert_into
table_file = r"PDF_path"
output_csv = r"out_csv"
df = convert_into(table_file, output_csv, output_format='csv', lattice=False, stream=True, multiple_tables=True, pages="all")

File names are cut while download to folder

My current code is cutting first 6 characters from file names while downloading PDF's. So for example PDF file name is 123456acII.pdf (https://example.com/wp-content/uploads/2016/11/123456acII.pdf) but file in folder is acII.pdf.
How to make names be as they are?
import os
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
main = "https://example.com/"
#If there is no such folder, the script will create one automatically
folder_location = r'C:\temp\webscraping'
if not os.path.exists(folder_location):os.mkdir(folder_location)
def Get_Links():
r = requests.get(main).text
soup = BeautifulSoup(r, 'html.parser')
links = []
for item in soup.findAll("div", {'class': 'large-4 medium-4 columns'}):
for n in item.find_all('a'):
print ('Link: '+ n.get('href'))
links.append(n.get('href'))
return links
def Parse_Links():
pdf = set()
for url in Get_Links():
r = requests.get(url).text
soup = BeautifulSoup(r, 'html.parser')
for item in soup.findAll("div", {'class': 'large-6 medium-8 columns large-centered'}):
for link in item.findAll("a"):
link = link.get("href")
if link:
pdf.add(link)
return pdf
def Save():
for item in Parse_Links():
print(f"Downloading File: {item[55:]}")
filename = os.path.join(folder_location,f"{item[55:]}")
r = requests.get(item)
with open(filename, 'wb') as f:
f.write(r.content)
print("done")
Save()

It looks like you are slicing the string starting at index position 55 {item[55:]}. Try to see if it's simply just starting your index position 6 positions prior:
change to: {item[49:]}

BeautifulSoup - scraping a forum page

I'm trying to scrape a forum discussion and export it as a csv file, with rows such as "thread title", "user", and "post", where the latter is the actual forum post from each individual.
I'm a complete beginner with Python and BeautifulSoup so I'm having a really hard time with this!
My current problem is that all the text is split into one character per row in the csv file. Is there anyone out there who can help me out? It would be fantastic if someone could give me a hand!
Here's the code I've been using:
from bs4 import BeautifulSoup
import csv
import urllib2
f = urllib2.urlopen("https://silkroad5v7dywlc.onion.to/index.php?action=printpage;topic=28536.0")
soup = BeautifulSoup(f)
b = soup.get_text().encode("utf-8").strip() #the posts contain non-ascii words, so I had to do this
writer = csv.writer(open('silkroad.csv', 'w'))
writer.writerows(b)

Ok here we go. Not quite sure what I'm helping you do here, but hopefully you have a good reason to be analyzing silk road posts.
You have a few issues here, the big one is that you aren't parsing the data at all. What you're essentially doing with .get_text() is going to the page, highlighting the whole thing, and then copying and pasting the whole thing to a csv file.
So here is what you should be trying to do:
Read the page source
Use soup to break it into sections you want
Save sections in parallel arrays for author, date, time, post, etc
Write data to csv file row by row
I wrote some code to show you what that looks like, it should do the job:
from bs4 import BeautifulSoup
import csv
import urllib2
# get page source and create a BeautifulSoup object based on it
print "Reading page..."
page = urllib2.urlopen("https://silkroad5v7dywlc.onion.to/index.php?action=printpage;topic=28536.0")
soup = BeautifulSoup(page)
# if you look at the HTML all the titles, dates,
# and authors are stored inside of <dt ...> tags
metaData = soup.find_all("dt")
# likewise the post data is stored
# under <dd ...>
postData = soup.find_all("dd")
# define where we will store info
titles = []
authors = []
times = []
posts = []
# now we iterate through the metaData and parse it
# into titles, authors, and dates
print "Parsing data..."
for html in metaData:
text = BeautifulSoup(str(html).strip()).get_text().encode("utf-8").replace("\n", "") # convert the html to text
titles.append(text.split("Title:")[1].split("Post by:")[0].strip()) # get Title:
authors.append(text.split("Post by:")[1].split(" on ")[0].strip()) # get Post by:
times.append(text.split(" on ")[1].strip()) # get date
# now we go through the actual post data and extract it
for post in postData:
posts.append(BeautifulSoup(str(post)).get_text().encode("utf-8").strip())
# now we write data to csv file
# ***csv files MUST be opened with the 'b' flag***
csvfile = open('silkroad.csv', 'wb')
writer = csv.writer(csvfile)
# create template
writer.writerow(["Time", "Author", "Title", "Post"])
# iterate through and write all the data
for time, author, title, post in zip(times, authors, titles, posts):
writer.writerow([time, author, title, post])
# close file
csvfile.close()
# done
print "Operation completed successfully."
EDIT: Included solution that can read files from directory and use data from that
Okay, so you have your HTML files in a directory. You need to get a list of files in the directory, iterate through them, and append to your csv file for each file in the directory.
This is the basic logic of our new program.
If we had a function called processData() that took a file path as an argument and appended data from the file to your csv file here is what it would look like:
# the directory where we have all our HTML files
dir = "myDir"
# our csv file
csvFile = "silkroad.csv"
# insert the column titles to csv
csvfile = open(csvFile, 'wb')
writer = csv.writer(csvfile)
writer.writerow(["Time", "Author", "Title", "Post"])
csvfile.close()
# get a list of files in the directory
fileList = os.listdir(dir)
# define variables we need for status text
totalLen = len(fileList)
count = 1
# iterate through files and read all of them into the csv file
for htmlFile in fileList:
path = os.path.join(dir, htmlFile) # get the file path
processData(path) # process the data in the file
print "Processed '" + path + "'(" + str(count) + "/" + str(totalLen) + ")..." # display status
count = count + 1 # increment counter
As it happens our processData() function is more or less what we did before, with a few changes.
So this is very similar to our last program, with a few small changes:
We write the column headers first thing
Following that we open the csv with the 'ab' flag to append
We import os to get a list of files
Here's what that looks like:
from bs4 import BeautifulSoup
import csv
import urllib2
import os # added this import to process files/dirs
# ** define our data processing function
def processData( pageFile ):
''' take the data from an html file and append to our csv file '''
f = open(pageFile, "r")
page = f.read()
f.close()
soup = BeautifulSoup(page)
# if you look at the HTML all the titles, dates,
# and authors are stored inside of <dt ...> tags
metaData = soup.find_all("dt")
# likewise the post data is stored
# under <dd ...>
postData = soup.find_all("dd")
# define where we will store info
titles = []
authors = []
times = []
posts = []
# now we iterate through the metaData and parse it
# into titles, authors, and dates
for html in metaData:
text = BeautifulSoup(str(html).strip()).get_text().encode("utf-8").replace("\n", "") # convert the html to text
titles.append(text.split("Title:")[1].split("Post by:")[0].strip()) # get Title:
authors.append(text.split("Post by:")[1].split(" on ")[0].strip()) # get Post by:
times.append(text.split(" on ")[1].strip()) # get date
# now we go through the actual post data and extract it
for post in postData:
posts.append(BeautifulSoup(str(post)).get_text().encode("utf-8").strip())
# now we write data to csv file
# ***csv files MUST be opened with the 'b' flag***
csvfile = open('silkroad.csv', 'ab')
writer = csv.writer(csvfile)
# iterate through and write all the data
for time, author, title, post in zip(times, authors, titles, posts):
writer.writerow([time, author, title, post])
# close file
csvfile.close()
# ** start our process of going through files
# the directory where we have all our HTML files
dir = "myDir"
# our csv file
csvFile = "silkroad.csv"
# insert the column titles to csv
csvfile = open(csvFile, 'wb')
writer = csv.writer(csvfile)
writer.writerow(["Time", "Author", "Title", "Post"])
csvfile.close()
# get a list of files in the directory
fileList = os.listdir(dir)
# define variables we need for status text
totalLen = len(fileList)
count = 1
# iterate through files and read all of them into the csv file
for htmlFile in fileList:
path = os.path.join(dir, htmlFile) # get the file path
processData(path) # process the data in the file
print "Processed '" + path + "'(" + str(count) + "/" + str(totalLen) + ")..." # display status
count = count + 1 # incriment counter