How does one "click" a subsidiary URL in Python, scrape that URL, and append those scraped data to the output of parent file?

Question

Python: Python 3.11.2 Python Editor: PyCharm 2022.3.3 (Community Edition) - Build PC-223.8836.43 OS: Windows 11 Pro, 22H2, 22621.1413 Browser: Chrome 111.0.5563.65 (Official Build) (64-bit)

---

Still a Baby Pythoneer, I'm scraping a URL https://dockets.justia.com/search?parties=Novo+Nordisk but also want to scrape its 10 hyperlinked pages (e.g., "https://dockets.justia.com/docket/puerto-rico/prdce/3:2023cv01127/175963,https://dockets.justia.com/docket/california/cacdce/2:2023cv01929/878409, etc.)

How do I (1) "open" the 10 hyperlinked pages, (2) scrape the information in the subsidiary, hyperlinked document, e.g., inside table-responsive with-gaps table-padding--small table-bordered table-padding-sides--small table-full-width, and then (3) append the captured information to the print output files (index) the parent URL.

I have looked into Selenium a bit to perhaps open and control the webpage that way, but it doesn't seem particularly applicable here. Do I really need Selenium for this or is there some nifty and simple way to do this?

This is what I have so far...

from bs4 import BeautifulSoup
import requests

html_text = requests.get("https://dockets.justia.com/search?parties=Novo+Nordisk").text
soup = BeautifulSoup(html_text, "lxml")
cases = soup.find_all("div", class_ = "has-padding-content-block-30 -zb")

# Printing to individual files
for index, case in enumerate(cases):
    case_number = case.find("span", class_ = "citation").text.replace(" ","")
    case_url = case.find("a", {"class": "case-name"})["href"]

    with open(f"posts/{index}.txt", "w") as f:
        f.write(f"Case No.: {case_number.strip()} \t")
        f.write(f"Case URL: {case_url} \n")
        print("File saved: {index}")

# If printing in terminal
# for case in cases:
#    case_number = case.find("span", class_ = "citation").text.replace(" ","")
#    case_url = case.find("a", {"class": "case-name"})["href"]
#    print(f"Case No.: {case_number.strip()}") # strip cleans off tags
#    print(f"Case URL: {case_url}")

Answer 1

from aiohttp import ClientSession
from pyuseragents import random
from bs4 import BeautifulSoup
from asyncio import run


class DocketsJustia:

    def __init__(self):
        self.headers = {
        'authority': 'dockets.justia.com',
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
        'accept-language': 'ro-RO,ro;q=0.9,en-US;q=0.8,en;q=0.7',
        'cache-control': 'max-age=0',
        'referer': 'https://dockets.justia.com/search?parties=Novo+Nordisk',
        'user-agent': random(),
        }

        self.PatchFile = "nametxt.txt"

    async def Parser(self, session):
        count = 1

        while True:
    
            params = {
                'parties': 'Novo Nordisk',
                'page': f'{count}',
                }

            async with session.get(f'https://dockets.justia.com/search?parties=Novo+Nordisk&page={count}', params=params) as response:
                links = BeautifulSoup(await response.text(), "lxml").find_all("div", {"class": "has-padding-content-block-30 -zb"})

                for link in links:
                    try:
                        case_link = link.find("a", {"class": "case-name"}).get("href")
                        case_number = link.find("span", {"class": "citation"}).text
                        print(case_number + "\t" + case_link + "\n")

                        with open(self.PatchFile, "a", encoding='utf-8') as file:
                            file.write(case_number + "\t" + case_link + "\n")
                    except:
                        pass
            count += 1
    async def LoggerParser(self):
        async with ClientSession(headers=self.headers) as session:
            await self.Parser(session)


def StartDocketsJustia():

    run(DocketsJustia().LoggerParser())


if __name__ == '__main__':
    StartDocketsJustia()