Leap forward

- added tests (pytest)
- use GET parameters to parse a page
- return an actual RSS feed

api/api/app.py

@@ -1,11 +0,0 @@
-from flask import Flask
-
-app = Flask(__name__)
-
-@app.route("/")
-def hello():
-    return "<p>Coucou.</p>"
-
-
-if __name__ == "__main__":
-    app.run()

api/api/feed.py

@@ -1,6 +1,8 @@
 from datetime import datetime
 
-from flask import Blueprint, make_response, render_template
+import validators
+from flask import Blueprint, jsonify, make_response, render_template, request
+from werkzeug.exceptions import HTTPException
 
 from api.db import get_db
 
@@ -9,11 +11,49 @@ from .scraper import scrape
 bp = Blueprint("feed", __name__, url_prefix="/feed")
 
 
+class InvalidParameters(Exception):
+    status_code = 400
+
+    def __init__(self, message, status_code=None, payload=None):
+        super().__init__()
+        self.message = message
+        if status_code is not None:
+            self.status_code = status_code
+        self.payload = payload
+
+    def to_dict(self):
+        rv = dict(self.payload or ())
+        rv["message"] = self.message
+        return rv
+
+
+@bp.errorhandler(InvalidParameters)
+def invalid_parameters(e):
+    return jsonify(e.to_dict()), e.status_code
+
+
 @bp.route("/", methods=("GET",))
 def parse_page():
-    link = "https://www.ouest-france.fr/bretagne/rennes-35000/"
-    feed = scrape(link)
+    args = dict(request.args)
+
+    # Checking if mandatory parameters are present
+    if not args.get("url"):
+        raise InvalidParameters("Missing parameter: URL")
+
+    if not args.get("title"):
+        raise InvalidParameters("Missing parameter: title")
+    
+    if not args.get("article"):
+        raise InvalidParameters("Missing parameter: article")
+
+    # Checking for correctness
+    if not args.get("url").startswith("https"):
+        args["url"] = "https://" + args.get("url")
+    if not validators.url(args.get("url")):
+        raise InvalidParameters("Incorrect URL")
+
+    feed = scrape(args)
     rss_xml = render_template("rss.xml", feed=feed, build_date=datetime.now())
     response = make_response(rss_xml)
-    response.headers['Content-Type'] = "application/rss+xml"
-    return response
+    response.headers["Content-Type"] = "application/rss+xml"
+    return response

api/api/scraper.py

@@ -5,16 +5,21 @@ import dateparser
 
 
 class FeedItem:
-    def __init__(self, title, content, author, link, item_datetime=datetime.now()):
+    def __init__(self, title, content, link, item_datetime=None, author=None):
         self.title = title
         self.content = content
-        self.author = author
         self.link = link
-        self.item_datetime = item_datetime.isoformat()
+        self.author = author
+        if item_datetime:
+            self.item_datetime = item_datetime.isoformat()
+        else:
+            self.item_datetime = None
     
     def __lt__(self, other):
         if self.item_datetime and other.item_datetime:
             return self.item_datetime < other.item_datetime
+        elif not self.title or not other.title:
+            return True
         else:
             return self.title < other.title
 
@@ -27,37 +32,82 @@ class Feed:
 
 
 @bt.request(output=None)
-def scrape(request, link):
-    soup = request.bs4(link)
-    section = soup.find("section", {"class": "liste-articles"})
-    articles = section.find_all("article", {"class": "teaser-media-liste"})
+def scrape(request, args):
+    soup = request.bs4(args.get("url"), timeout=5)
 
-    feed = Feed(title=soup.title.get_text(), url=link, items=[])
+    # If section is provided, use it, else use the entire page/soup
+    section = soup
+    if args.get("section"):
+        section_class = None
+        if args.get("sectionClass"):
+            section_class = {"class": args.get("sectionClass")}
+        section = soup.find(args.get("section"), section_class)
+
+    article_class = None
+    if args.get("articleClass"):
+        article_class = {"class": args.get("articleClass")}
+    articles = section.find_all(args.get("article"), article_class)
+
+    feed = Feed(title=soup.title.get_text(), url=args.get("url"), items=[])
 
     for article in articles:
-        title = article.find("h2")
+        title_class = None
+        if args.get("titleClass"):
+            title_class = {"class": args.get("titleClass")}
+        title = article.find(args.get("title"), title_class)
         if title:
             title = title.get_text()
 
-        content = article.find("p")
-        if content:
-            content = content.get_text()
+        content_tag = "p"
+        content_class = None
+        if args.get("content"):
+            content_tag = args.get("content")
+        if args.get("contentClass"):
+            content_class = {"class": args.get("contentClass")}
+        paragraphs = article.find_all(content_tag, content_class)
+        content = ""
+        if paragraphs:
+            content = "<br>".join([p.get_text() for p in paragraphs])
 
-        link = article.find("a", {"class": "titre-lien"})
+        link_tag = "a"
+        link_class = None
+        if args.get("link"):
+            link_tag = args.get("link")
+        if args.get("linkClass"):
+            link_class = {"class": args.get("linkClass")}
+        link = article.find(link_tag, link_class)
         if link:
             link = link["href"]
 
-        item_datetime = article.find("time")
-        if item_datetime:
-            item_datetime = dateparser.parse(item_datetime["datetime"])
+        item_datetime = None
+        item_datetime_class = None
+        if args.get("datetime"):
+            if args.get("datetimeClass"):
+                item_datetime_class = {"class": args.get("datetimeClass")}
+            item_datetime = article.find(args.get("datetime"), item_datetime_class)
+            if item_datetime:
+                item_datetime = dateparser.parse(item_datetime["datetime"])
+
+        author = None
+        author_class = None
+        if args.get("author"):
+            if args.get("authorClass"):
+                author_class = {"class": args.get("authorClass")}
+            author = article.find(args.get("author"), author_class)
+        
         item = FeedItem(
             title=title,
             content=content,
-            author="Ouest-France",
             link=link,
             item_datetime=item_datetime,
+            author=author
         )
-        feed.items.append(item)
+
+        if item.title is not None:
+            feed.items.append(item)
+    
+    # Sort by datetime if any
+    if args.get("datetime"):
         feed.items.sort(reverse=True)
 
     return feed

api/api/templates/rss.xml

@@ -2,9 +2,9 @@
 <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
 <channel>
   <title>{{ feed.title }}</title>
-  <atom:link href="{{ request.base_url }}" rel="self" type="application/rss+xml"/>
-  <link>{{ request.base_url }}</link>
-  <description>A feed generated from {{feed.url}} with Rudibridge</description>
+  <atom:link href="{{ request.url }}" rel="self" type="application/rss+xml"/>
+  <link>{{ request.url }}</link>
+  <description>A feed generated from {{ feed.url }} with Rudibridge</description>
   <lastBuildDate>{{ build_date.strftime("%a, %d %b %Y %T") }} +0000</lastBuildDate>
   {% for item in feed.items %}
   <item>
@@ -21,6 +21,9 @@
   {% if item.item_datetime %}
   <pubDate>{{ item.item_datetime }}</pubDate>
   {% endif %}
+  {% if item.author %}
+  <author>{{ item.author }}</author>
+  {% endif %}
   </item>
   {% endfor %}
 </channel>

api/poetry.lock

@@ -1149,6 +1149,17 @@ brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotl
 secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
+[[package]]
+name = "validators"
+version = "0.28.1"
+description = "Python Data Validation for Humans™"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "validators-0.28.1-py3-none-any.whl", hash = "sha256:890c98789ad884037f059af6ea915ec2d667129d509180c2c590b8009a4c4219"},
+    {file = "validators-0.28.1.tar.gz", hash = "sha256:5ac88e7916c3405f0ce38ac2ac82a477fcf4d90dbbeddd04c8193171fc17f7dc"},
+]
+
 [[package]]
 name = "werkzeug"
 version = "3.0.2"
@@ -1183,4 +1194,4 @@ h11 = ">=0.9.0,<1"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "570ed3ea32a7c870f94ad73cdc122034842353bbef4e7c6111dcd150f79394ac"
+content-hash = "d0e30c9d7e8186fec20b1716f1a47e7e759e26cd68c5af13bd1ef4b9259426dd"

api/pyproject.toml

@@ -15,6 +15,7 @@ coverage = "^7.5.1"
 requests = "^2.31.0"
 botasaurus = "^4.0.14"
 dateparser = "^1.2.0"
+validators = "^0.28.1"
 
 
 [build-system]

api/tests/conftest.py

@@ -0,0 +1,15 @@
+import pytest
+from api import create_app
+
+@pytest.fixture()
+def app():
+    app = create_app()
+    app.config.update({
+        "TESTING": True
+    })
+
+    yield app
+
+@pytest.fixture()
+def client(app):
+    return app.test_client()

api/tests/test_parameters.py

@@ -0,0 +1,35 @@
+import pytest
+
+
+@pytest.mark.parametrize(
+    "url,missing_parameter",
+    [
+        ("/feed/", "URL"),
+        ("/feed/?url=https://mozilla.org", "title"),
+        ("/feed/?url=https://mozilla.org&title=h2", "article"),
+        ("/feed/?url=https://mozilla.org&title=h2&article=article", None),
+    ],
+)
+def test_missing_parameters(client, url, missing_parameter):
+    response = client.get(url)
+
+    if missing_parameter:
+        assert response.json["message"] == f"Missing parameter: {missing_parameter}"
+        assert response.status_code == 400
+    else:
+        assert response.status_code == 200
+
+
+@pytest.mark.parametrize(
+    "url,status_code,message",
+    [
+        ("https://mozilla.org", 200, None),
+        ("mozilla.org", 200, None),
+        ("toto", 400, "Incorrect URL"),
+    ],
+)
+def test_incorrect_url(client, url, status_code, message):
+    response = client.get(f"/feed/?url={url}&title=h2&article=article")
+    assert response.status_code == status_code
+    if message:
+        assert response.json["message"] == message