This is a quick and dirty script to get a dataframe of parties to SC Supreme Court cases that have filed opinions. This is the first step to extracting information about opinions filed by the Court. NOT ALL EDGE CASES ARE HANDLED YET.

get_opinion_parties.py

import pandas as pd
import requests
from io import BytesIO
import urllib
from pathlib import Path
import pdfplumber

headers = {'user-agent': 'INSERT YOUR DESIRED USER AGENT HERE'):
def extract_text_between(start_text, stop_text, full_text):
    start_index = full_text.find(start_text) + len(start_text)
    stop_index = full_text.find(stop_text)
    if start_index == -1 or stop_index == -1:
        return "Both start or stop text not found in the input string."
    extracted_text = full_text[start_index:stop_index]
    return extracted_text

def get_pdf(url):
    print(url)
    return BytesIO(requests.get(url,headers=headers).content)

def get_fonts(pdf_byte_array):
    #resp = BytesIO(requests.get(url,headers=headers).content)
    with pdfplumber.open(pdf_byte_array) as pdf:
        meta = pdf.metadata
        font_sizes = sorted(set([x['size'] for x in pdf.chars]))
    sizes=set([round(size,0) for size in font_sizes])
    print(meta)
    print(sizes)

    print(len(sizes))

pdfs = [f'https://www.sccourts.org/opinions/HTMLFiles/SC/{x}.pdf' for x in range(28000,28228)] 
pdf_bytes = [(pdf,get_pdf(pdf)) for pdf  in pdfs]
pdf_dict = dict(pdf_bytes)
cases = []
max_parties = 0
case_max_parties = ''
for case_url,pdf_bytes in pdf_dict.items():
    print('-----------------')
    print(case_url)
    with pdfplumber.open(pdf_bytes) as pdf:
        first_party = None
        second_party = None
        third_party = None
        fourth_party = None
        single_party = False
        case_num = Path(urllib.parse.urlparse(case_url).path).stem.split('/')[-1]
        print(case_num)
        rects = pdf.rects
        if len(rects) == 0:
            print("BAD FORMAT")
            continue
        page = rects[0]['page_number']

        infoblock = ""
        if page != 0:
            for curr_page in range(0,page):
                if page != curr_page:
                    infoblock+= pdf.pages[curr_page].extract_text()
                else:
                    infoblock+=pdf.pages[curr_page].crop((0,0,612,rects[0]['top'])).extract_text()
        #print(case_url)
        #print('--')
        else:
            infoblock = pdf.pages[0].crop((0,0,612,rects[0]['top'])).extract_text()
        #print(infoblock)
        #print(case_url)
        if "in the matter of" not in infoblock.lower(): #and '\nand\n' not in infoblock.lower():
            if "In The Supreme Court" in infoblock:
                parties = extract_text_between('THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n','\nAppellate Case',infoblock).split('\nv.\n')
            else:
                parties = extract_text_between('The Supreme Court of South Carolina\n','\nAppellate Case', infoblock).split('\nv.\n')
            for i, party in enumerate(parties):
                if i == 0:
                    first_party = party  # Assuming the first party is at index 0
                elif i == 1:
                    second_party = party
                elif i == 2:
                    third_party = party
                elif i == 3:
                    fourth_party = party
            #if len(parties) > max_parties:
            #    max_parties = len(parties)
            #    case_max_parties = case_num
            #print("FIRST_PARTY:\t" + extract_text_between('THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n',',\nv.\n',infoblock))
            #first_party = extract_text_between('THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n',',\nv.\n',infoblock)
            #print("SECOND PARTY:\t" + extract_text_between("\nv.\n","Appellate Case",infoblock))
            #second_party = extract_text_between("\nv.\n","Appellate Case",infoblock)
            #print(get_fonts(pdf_bytes))
        #if "\nAnd\n" in infoblock:
        #    cases = "FIRST_PARTY:\t" + extract_text_between('THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n','Appellate Case',infoblock)
        #    for i in cases.split('\nAnd\n'):
        #        print(repr(i))
        #        print('FOUND')
        elif "in the matter of" in infoblock.lower():
            single_party = True
            if "THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n" in infoblock:
                print(extract_text_between("THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n","\nAppellate Case",infoblock))
                first_party = extract_text_between("THE STATE OF SOUTH CAROLINA\nIn The Supreme Court\n","\nAppellate Case",infoblock)
            elif "The Supreme Court of South Carolina\nIn the Matter of" in infoblock:
                print(extract_text_between("The Supreme Court of South Carolina\n","\nAppellate Case",infoblock))
                first_party = extract_text_between("The Supreme Court of South Carolina\n","\nAppellate Case",infoblock)
        #else:
        #    break
        pdf.close()
        cases.append({"case_num":case_num,
                      "single_party":single_party,
                      "first_party":first_party,
                      "second_party":second_party,
                      "third_party":third_party,
                      "fourth_party":fourth_party
        })

df=pd.DataFrame(cases)
df['url']= 'https://www.sccourts.org/opinions/HTMLFiles/SC/' + df.case_num + '.pdf'