Unable to write results in a csv file in some customized manner

Question

I've created a script to parse the singers , their concerning links , actors and their concerning links out of different containers from a webpage. The script is doing fine. What I can't do is write the results in a csv file accordingly.

Webpage link

I've tried with:

import csv
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

base_url = 'https://www.hindigeetmala.net'
link = 'https://www.hindigeetmala.net/movie/2_states.htm'

res = requests.get(link)
soup = BeautifulSoup(res.text,"lxml")

with open("hindigeetmala.csv","w",newline="") as f:
    writer = csv.writer(f)
    writer.writerow(['singer_records','actor_records'])

    for item in soup.select("tr[itemprop='track']"):
        try:
            singers = [i.get_text(strip=True) for i in item.select("span[itemprop='byArtist']") if i.get_text(strip=True)]
        except Exception: singers = ""

        try:
            singer_links = [urljoin(base_url,i.get("href")) for i in item.select("a:has(> span[itemprop='byArtist'])") if i.get("href")]
        except Exception: singer_links = ""
        singer_records = [i for i in zip(singers,singer_links)]

        try:
            actors = [i.get_text(strip=True) for i in item.select("a[href^='/actor/']") if i.get("href")]
        except Exception: actors = ""
        try:
            actor_links = [urljoin(base_url,i.get("href")) for i in item.select("a[href^='/actor/']") if i.get("href")]
        except Exception: actor_links = ""
        actor_records = [i for i in zip(actors,actor_links)]
        song_name = item.select_one("span[itemprop='name']").get_text(strip=True)
        writer.writerow([singer_records,actor_records,song_name])
        print(singer_records,actor_records,song_name)

If I execute the script as is, this is the output I get.

When I try like writer.writerow([*singer_records,*actor_records,song_name]) , I get this type of output . Only the first pair of tuple is written.

This is my expected output .

How can I write the result, as in name and their links in a csv file according to the third image?

PS All the images of the output represent the first column of csv files for brevity.

Answer 1

with feedback from SIM, I think this is what you looking for (I just added one function for formatting your lists)

import csv
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

base_url = 'https://www.hindigeetmala.net'
link = 'https://www.hindigeetmala.net/movie/2_states.htm'

res = requests.get(link)
soup = BeautifulSoup(res.text, "lxml")


def merge_results(inpt):
    return [','.join(nested_items for nested_items in
                     [','.join("'" + tuple_item + "'" for tuple_item in item)
                      for item in inpt])]


with open("hindigeetmala.csv", "w", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(['singer_records', 'actor_records'])

    for item in soup.select("tr[itemprop='track']"):
        try:
            singers = [i.get_text(strip=True) for i in item.select(
                "span[itemprop='byArtist']") if i.get_text(strip=True)]
        except Exception:
            singers = ""

        try:
            singer_links = [urljoin(base_url, i.get("href")) for i in item.select(
                "a:has(> span[itemprop='byArtist'])") if i.get("href")]
        except Exception:
            singer_links = ""
        singer_records = [i for i in zip(singers, singer_links)]

        try:
            actors = [i.get_text(strip=True) for i in item.select(
                "a[href^='/actor/']") if i.get("href")]
        except Exception:
            actors = ""
        try:
            actor_links = [urljoin(base_url, i.get("href")) for i in item.select(
                "a[href^='/actor/']") if i.get("href")]
        except Exception:
            actor_links = ""
        actor_records = [i for i in zip(actors, actor_links)]
        song_name = item.select_one(
            "span[itemprop='name']").get_text(strip=True)
        writer.writerow(merge_results(singer_records) +
                        merge_results(actor_records)+[song_name])
        print(singer_records, actor_records, song_name)