Legal Research Web Scraping with CAPTCHA Handling

Legal databases, court filing systems, and case law repositories protect their data with CAPTCHAs. Law firms, legal tech companies, and compliance teams need automated access to search case law, monitor filings, and aggregate regulatory data. CaptchaAI handles CAPTCHA challenges on these portals.

Legal Data Sources and CAPTCHAs

Case Law Search Engine

import requests
import time
import re
import base64
from bs4 import BeautifulSoup
import csv

CAPTCHAAI_KEY = "YOUR_API_KEY"
CAPTCHAAI_URL = "https://ocr.captchaai.com"


def solve_recaptcha(sitekey, pageurl):
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "userrecaptcha",
        "googlekey": sitekey, "pageurl": pageurl, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(60):
        time.sleep(5)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


def solve_image_captcha(image_bytes):
    img_b64 = base64.b64encode(image_bytes).decode()
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "base64",
        "body": img_b64, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(20):
        time.sleep(3)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


class LegalResearchScraper:
    def __init__(self, proxy=None):
        self.session = requests.Session()
        if proxy:
            self.session.proxies = {"http": proxy, "https": proxy}
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 Chrome/126.0.0.0 Safari/537.36",
        })

    def search_cases(self, search_url, query, sitekey=None, max_pages=5):
        """Search case law database."""
        all_cases = []

        for page in range(max_pages):
            url = f"{search_url}?q={query}&page={page + 1}"
            resp = self.session.get(url, timeout=30)

            if self._has_captcha(resp.text):
                if sitekey:
                    token = solve_recaptcha(sitekey, url)
                    resp = self.session.post(url, data={
                        "q": query,
                        "g-recaptcha-response": token,
                    })
                else:
                    resp = self._solve_image_and_retry(resp.text, url, query)

            cases = self._parse_cases(resp.text)
            if not cases:
                break

            all_cases.extend(cases)
            print(f"Page {page + 1}: {len(cases)} cases")
            time.sleep(5)

        return all_cases

    def get_case_details(self, case_url):
        """Fetch full case details."""
        resp = self.session.get(case_url, timeout=30)

        if self._has_captcha(resp.text):
            sitekey = self._extract_sitekey(resp.text)
            if sitekey:
                token = solve_recaptcha(sitekey, case_url)
                resp = self.session.post(case_url, data={
                    "g-recaptcha-response": token,
                })

        soup = BeautifulSoup(resp.text, "html.parser")
        return {
            "title": self._text(soup, "h1, .case-title"),
            "citation": self._text(soup, ".citation, .case-cite"),
            "court": self._text(soup, ".court, .jurisdiction"),
            "date": self._text(soup, ".decision-date, .date-decided"),
            "judge": self._text(soup, ".judge, .authored-by"),
            "summary": self._text(soup, ".summary, .headnote"),
            "url": case_url,
        }

    def monitor_docket(self, docket_url, case_number, sitekey=None):
        """Monitor a specific case docket for new filings."""
        resp = self.session.get(docket_url, timeout=30)

        data = {"case_number": case_number}
        if sitekey and self._has_captcha(resp.text):
            token = solve_recaptcha(sitekey, docket_url)
            data["g-recaptcha-response"] = token

        resp = self.session.post(docket_url, data=data)
        return self._parse_docket(resp.text)

    def export_results(self, cases, filename):
        """Export case results to CSV."""
        if not cases:
            return
        with open(filename, "w", newline="", encoding="utf-8") as f:
            writer = csv.DictWriter(f, fieldnames=cases[0].keys())
            writer.writeheader()
            writer.writerows(cases)

    def _has_captcha(self, html):
        return any(tag in html.lower() for tag in [
            'data-sitekey', 'g-recaptcha', 'captcha',
        ])

    def _extract_sitekey(self, html):
        match = re.search(r'data-sitekey="([^"]+)"', html)
        return match.group(1) if match else None

    def _solve_image_and_retry(self, html, url, query):
        match = re.search(r'src="(/captcha[^"]+)"', html)
        if match:
            img_url = url.split("?")[0].rstrip("/") + match.group(1)
            img = self.session.get(img_url)
            answer = solve_image_captcha(img.content)
            return self.session.post(url, data={
                "q": query,
                "captcha": answer,
            })
        return self.session.get(url)

    def _parse_cases(self, html):
        soup = BeautifulSoup(html, "html.parser")
        cases = []
        for item in soup.select(".case-result, .search-result, tr.result"):
            title_el = item.select_one("a, .case-name")
            if title_el:
                cases.append({
                    "title": title_el.get_text(strip=True),
                    "url": title_el.get("href", ""),
                    "citation": self._text(item, ".citation, .cite"),
                    "date": self._text(item, ".date"),
                    "court": self._text(item, ".court"),
                })
        return cases

    def _parse_docket(self, html):
        soup = BeautifulSoup(html, "html.parser")
        entries = []
        for row in soup.select(".docket-entry, tr.filing"):
            entries.append({
                "date": self._text(row, ".date, td:first-child"),
                "entry": self._text(row, ".description, td:nth-child(2)"),
                "filed_by": self._text(row, ".filer, td:nth-child(3)"),
            })
        return entries

    def _text(self, el, selector):
        found = el.select_one(selector)
        return found.get_text(strip=True) if found else ""


# Usage
scraper = LegalResearchScraper(
    proxy="http://user:pass@residential.proxy.com:5000"
)

# Search case law
cases = scraper.search_cases(
    search_url="https://caselaw.example.com/search",
    query="data privacy GDPR",
    max_pages=5,
)

# Get details for relevant cases
for case in cases[:10]:
    if case["url"]:
        details = scraper.get_case_details(case["url"])
        print(f"{details['citation']}: {details['title']}")
        time.sleep(3)

# Export results
scraper.export_results(cases, "gdpr_cases.csv")

Regulatory Monitoring

class RegulatoryMonitor:
    def __init__(self, proxy=None):
        self.scraper = LegalResearchScraper(proxy=proxy)
        self.seen_entries = set()

    def check_new_filings(self, feeds):
        """Check regulatory portals for new filings."""
        new_filings = []

        for feed in feeds:
            try:
                cases = self.scraper.search_cases(
                    feed["url"], feed["query"],
                    sitekey=feed.get("sitekey"),
                    max_pages=2,
                )

                for case in cases:
                    key = case.get("citation") or case.get("title")
                    if key and key not in self.seen_entries:
                        self.seen_entries.add(key)
                        case["source"] = feed["name"]
                        new_filings.append(case)

            except Exception as e:
                print(f"Error checking {feed['name']}: {e}")

            time.sleep(5)

        return new_filings

Troubleshooting

FAQ

Is automated access to court records legal?

Public court records are generally accessible. PACER charges per-page fees regardless of access method. Always respect system rate limits and terms of use.

How do I handle PACER fees?

PACER charges per page. Budget for fees when planning bulk data collection. Consider RECAP (free archive) for already-downloaded documents.

Which legal databases have the most CAPTCHAs?

State court systems are worst — many use older image CAPTCHAs. Federal courts (PACER) use reCAPTCHA v2. Patent databases also frequently trigger CAPTCHAs.

Related Guides

• Government Portal Automation
• Academic Research Scraping
• Rotating Residential Proxies

Streamline legal research — get your CaptchaAI key and automate case law and filing searches.