middleburycampus.com APIwww.middleburycampus.com ↗

curl -X GET 'https://api.parse.bot/scraper/54e52fbb-5d0c-426e-be2c-2a020b66fad2/search_articles?page=1&query=climate&per_page=20' \
  -H 'X-API-Key: $PARSE_API_KEY'

"""
Middlebury Campus News API Client
Get your API key from: https://parse.bot/settings
"""

import os
import requests
from typing import Optional, Dict, Any, List


class ParseClient:
    """Client for Middlebury Campus News API"""

    def __init__(self, api_key: Optional[str] = None):
        self.base_url = "https://api.parse.bot"
        self.scraper_id = "54e52fbb-5d0c-426e-be2c-2a020b66fad2"
        self.api_key = api_key or os.getenv("PARSE_API_KEY")

        if not self.api_key:
            raise ValueError("API key required. Set PARSE_API_KEY env var or pass api_key parameter.")

    def _call(self, endpoint: str, method: str = "POST", **params) -> Dict[str, Any]:
        """Make API call to Parse endpoint"""
        url = f"{self.base_url}/scraper/{self.scraper_id}/{endpoint}"
        headers = {
            "X-API-Key": self.api_key,
            "Content-Type": "application/json"
        }

        if method == "GET":
            response = requests.get(url, headers=headers, params=params)
        elif method == "POST":
            response = requests.post(url, headers=headers, json=params)
        else:
            raise ValueError(f"Unsupported method: {method}")

        response.raise_for_status()
        return response.json()

    def search_articles(self, query: str, page: int = 1, per_page: int = 20) -> Dict[str, Any]:
        """
        Search articles across The Middlebury Campus archives.

        Args:
            query: Search keywords to match against article content and titles
            page: Page number for pagination (default: 1)
            per_page: Number of results per page (default: 20)

        Returns:
            Dictionary with search results, total count, and articles
        """
        return self._call(
            "search_articles",
            method="GET",
            query=query,
            page=page,
            per_page=per_page
        )

    def get_article(self, article_slug: str) -> Dict[str, Any]:
        """
        Retrieve full content of a single article.

        Args:
            article_slug: Article URL slug in format YYYY/MM/article-title-slug

        Returns:
            Dictionary with article title, content, authors, date, and metadata
        """
        return self._call(
            "get_article",
            method="GET",
            article_slug=article_slug
        )

    def list_section_articles(
        self,
        section: str = "news",
        page: int = 1,
        per_page: int = 20
    ) -> Dict[str, Any]:
        """
        List articles from a specific section.

        Args:
            section: Section slug (news, local, arts-culture, opinion, sports)
            page: Page number for pagination (default: 1)
            per_page: Number of results per page (default: 20)

        Returns:
            Dictionary with paginated articles from the section
        """
        return self._call(
            "list_section_articles",
            method="GET",
            section=section,
            page=page,
            per_page=per_page
        )


def main():
    """Practical workflow: search for articles, then fetch full content of top results"""

    client = ParseClient()

    # Step 1: Search for articles about climate change
    print("=" * 70)
    print("SEARCHING FOR CLIMATE-RELATED ARTICLES")
    print("=" * 70)

    search_results = client.search_articles(query="climate", page=1, per_page=5)

    if search_results.get("status") == "success":
        data = search_results.get("data", {})
        total = data.get("total", 0)
        articles = data.get("articles", [])

        print(f"\nFound {total} articles matching 'climate'")
        print(f"Showing page 1 with {len(articles)} results:\n")

        for idx, article in enumerate(articles, 1):
            print(f"{idx}. {article.get('title')}")
            print(f"   Date: {article.get('date')}")
            print(f"   Snippet: {article.get('snippet', '')[:100]}...")
            print()

        # Step 2: Get full content of the first search result
        if articles:
            first_article_url = articles[0].get("url", "")

            # Extract slug from URL (format: 2026/05/article-title-slug)
            if "/article/" in first_article_url:
                article_slug = first_article_url.split("/article/")[-1]

                print("=" * 70)
                print("FETCHING FULL CONTENT OF TOP ARTICLE")
                print("=" * 70)

                full_article = client.get_article(article_slug=article_slug)

                if full_article.get("status") == "success":
                    article_data = full_article.get("data", {})

                    print(f"\nTitle: {article_data.get('title')}")
                    print(f"Category: {article_data.get('category')}")
                    print(f"Date: {article_data.get('date')}")

                    authors = article_data.get("authors", [])
                    if authors:
                        author_names = ", ".join([a.get("name") for a in authors])
                        print(f"Authors: {author_names}")

                    if article_data.get("image_url"):
                        print(f"Featured Image: {article_data.get('image_url')}")

                    content = article_data.get("content", "")
                    print(f"\nContent (first 500 chars):\n{content[:500]}...")

    # Step 3: Browse sports section
    print("\n" + "=" * 70)
    print("BROWSING SPORTS SECTION")
    print("=" * 70)

    sports_results = client.list_section_articles(section="sports", page=1, per_page=5)

    if sports_results.get("status") == "success":
        data = sports_results.get("data", {})
        section = data.get("section", "")
        total_pages = data.get("total_pages", 0)
        articles = data.get("articles", [])

        print(f"\nSection: {section.upper()}")
        print(f"Total pages: {total_pages}")
        print(f"Articles on this page:\n")

        for idx, article in enumerate(articles, 1):
            print(f"{idx}. {article.get('title')}")
            print(f"   Date: {article.get('date')}")

            authors = article.get("authors", [])
            if authors:
                print(f"   Authors: {', '.join(authors)}")
            print()


if __name__ == "__main__":
    main()