CODEWITHSUNDEEP
pythonfor-loopweb-scraping
Filip Chobodicky
Filip Chobodicky

Reputation: 67

Python For loop inside for loop

Can someone help me with the for loop inside for loop (pdfname)?

The output should be: Roco 23380 Instructions (DE), Roco 23380 (DE), ...

I have this output now:

enter image description here

This is source:

enter image description here

This is my code:

import requests
from bs4 import BeautifulSoup
import pandas as pd
import xlsxwriter
import re
import os

productlinks = []

for x in range(1, 2):
    r = requests.get(
        f'https://www.roco.cc/ren/products/locomotives/steam-locomotives.html?p={x}&verfuegbarkeit_status=41%2C42%2C43%2C45%2C44')
    soup = BeautifulSoup(r.content, 'lxml')
    productlist = soup.find_all('li', class_='item product product-item')

    for item in productlist:
        for link in item.find_all('a', class_='product-item-link', href=True):
            productlinks.append(link['href'])

pdflist = []

for url in productlinks:
    r = requests.get(url, allow_redirects=False)
    soup = BeautifulSoup(r.content, 'html.parser')
    for tag in soup.find_all('a'):
        on_click = tag.get('onclick')
        if on_click:
            pdf = re.findall(r"'([^']*)'", on_click)[0]
            if 'pdf' in pdf:

                name = 'Roco'

            try:
                reference = soup.find(
                    'span', class_='product-head-artNr').get_text().strip()
            except Exception as e:
                print(e)

            
            try:
                pdfname = soup.find('td', class_='col-download-data').get_text().strip()
            except Exception as e:
                print(e)

            print(name, reference, pdfname)

Upvotes: 1

Views: 102

Answers (3)

Filip Chobodicky
Filip Chobodicky

Reputation: 67

Thanks for help, guys. Finished one part of code:

    try:
        os.mkdir(os.path.join(os.getcwd(), pdffolder))
    except:
        pass
    os.chdir(os.path.join(os.getcwd(), pdffolder))

    for url in productlinks:
        r = requests.get(url, allow_redirects=False)
        soup = BeautifulSoup(r.content, 'html.parser')
        num_of_pdfs = 0
        for tag in soup.find_all('a'):
            on_click = tag.get('onclick')
            if on_click:
                pdf = re.findall(r"'([^']*)'", on_click)[0]
                if 'pdf' in pdf:

                    name = 'Roco'

                try:
                    reference = soup.find(
                        'span', class_='product-head-artNr').get_text().strip()
                except Exception as e:
                    print(e)

                try:
                    pdfname = soup.findAll(
                        'td', class_='col-download-data')[num_of_pdfs].get_text().strip().lower()
                    pdfname = pdfname.replace(' ', '_')
                    num_of_pdfs += 1
                except Exception as e:
                    print(e)

                pdflist.append(pdf)

                with open(name + '-' + reference + '-' + pdfname + '-' + '.pdf', 'wb') as f:
                    im = requests.get(pdf)
                    f.write(im.content)

                pdfs = {
                    'Manufacturer_name': name,
                    'Reference': reference,
                    'Documents': name + '_' + reference + '_' + pdfname + '.pdf'
                }

                doculist.append(pdfs)


pdfpath('Rocco - pdf')

Upvotes: 1

PRStark
PRStark

Reputation: 1258

Replace this

    try:
        pdfname = soup.find('td', class_='col-download-data').get_text().strip()
    except Exception as e:
        print(e)

with this:

        try:
            pdfname = ""
            for tag in soup.find_all('td',  class_='col-download-data'):
              pdfname = pdfname + "," + tag.get_text().strip()
            
        except Exception as e:
          print(e)

Upvotes: 1

Teddy
Teddy

Reputation: 594

You can use findAll instead of find to get all names and then use a variable to keep track of which pdfname should be used.

for url in productlinks:
    r = requests.get(url, allow_redirects=False)
    soup = BeautifulSoup(r.content, 'html.parser')
    # set variable to 0
    num_of_pdfs = 0
    for tag in soup.find_all('a'):
        on_click = tag.get('onclick')
        if on_click:
            pdf = re.findall(r"'([^']*)'", on_click)[0]

            if 'pdf' in pdf:
                name = 'Roco'

            try:
                reference = soup.find(
                    'span', class_='product-head-artNr').get_text().strip()
            except Exception as e:
                print(e)

            try:
                # use find all and use the current pdf as index
                pdfname = soup.findAll('td', class_='col-download-data')[num_of_pdfs].get_text().strip()
                # increment num_of_pdfs to get the next name on next iteration
                num_of_pdfs += 1
            except Exception as e:
                print(e)

            print(name, reference, pdfname)

Upvotes: 1

Related Questions