Increased element field from 255 to 1000 characters

README.md

@@ -28,7 +28,7 @@ HRSS is an application that allows you to transform any website into a RSS feed.
 
 [Because we all love demos.](https://hrss.hipstercat.fr)
 
-# Installation
+# Installation (native)
 
  1. Make sure you have Python3 installed and virtualenv.
  2. Clone this repo for unstable branch, or download [latest release](https://hipstercat.fr/gogs/hipstercat/hrss/releases).
@@ -36,4 +36,7 @@ HRSS is an application that allows you to transform any website into a RSS feed.
  4. `bin/activate && pip3 install -r requirements.txt` to install dependencies.
  5. `python3 manage.py migrate` to apply latest DB migrations (and create the H2 database file).
  6. `python3 manage.py runserver` to run the integrated webserver (not suitable for production use - even though you should not use HRSS in a production environnement at all until it is considered stable anyway). Use uWSGI to run it in a production environnement.
- 
+ 
+# Installation (Docker)
+
+ Use https://github.com/kmlucy/docker-hrss nicely made by [kmlucy](https://github.com/kmlucy).

hrss/settings.py

@@ -11,6 +11,7 @@ https://docs.djangoproject.com/en/2.0/ref/settings/
 """
 
 import os
+import urllib.parse
 
 # Build paths inside the project like this: os.path.join(BASE_DIR, ...)
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@@ -27,6 +28,9 @@ DEBUG = True
 
 ALLOWED_HOSTS = []
 
+# Set up your website base URL here, WITHOUT A TRAILING SLASH.
+BASE_URL = "http://localhost:8000"
+
 
 # Application definition
 
@@ -119,7 +123,43 @@ USE_TZ = True
 # Static files (CSS, JavaScript, Images)
 # https://docs.djangoproject.com/en/2.0/howto/static-files/
 
-STATIC_URL = '/static/'
+STATIC_URL = '/'+urllib.parse.urlparse(BASE_URL).path[1:]+'/static/' if urllib.parse.urlparse(BASE_URL).path[1:] else '/static/'
 STATIC_ROOT = os.path.join(BASE_DIR, 'static')
 
-USE_X_FORWARDED_HOST = True
+USE_X_FORWARDED_HOST = True
+
+LOGGING = {
+    'version': 1,
+    'disable_existing_loggers': False,
+    'formatters': {
+        'verbose': {
+            'format': '[%(asctime)s] [%(levelname)s] [%(module)s] %(message)s'
+        },
+        'simple': {
+            'format': '%(levelname)s %(message)s'
+        },
+    },
+    'handlers': {
+        'file': {
+            'class': 'logging.FileHandler',
+            'filename': 'debug.log',
+            'formatter': 'verbose'
+        },
+        'console': {
+            'class': 'logging.StreamHandler',
+            'formatter': 'verbose'
+        },
+    },
+    'loggers': {
+        'web': {
+            'handlers': ['console', 'file'],
+            'level': 'DEBUG',
+        },
+        'django': {
+            'handlers': ['console', 'file'],
+            'level': 'ERROR',
+        }
+    }
+}
+
+X_FRAME_OPTIONS = 'SAMEORIGIN'

hrss/urls.py

@@ -16,8 +16,12 @@ Including another URLconf
 from django.contrib import admin
 from django.urls import path
 from django.conf.urls import include, url
+from django.conf import settings
+import urllib.parse
+base_path = urllib.parse.urlparse(settings.BASE_URL).path[1:]
+
 
 urlpatterns = [
-    path('admin/', admin.site.urls),
-    url(r'', include('web.urls')),
+    path(base_path+'/admin/' if base_path else 'admin/', admin.site.urls),
+    url(base_path+'/' if base_path else '', include('web.urls')),
 ]

requirements.txt

@@ -0,0 +1,4 @@
+Django>=2.1.2
+beautifulsoup4>=4.6.3
+requests>=2.20.0
+html5lib>=1.0.1

web/admin.py

@@ -1,3 +1,4 @@
 from django.contrib import admin
+from .models import Feed
 
-# Register your models here.
+admin.site.register(Feed)

web/context_processor.py

@@ -1,11 +1,9 @@
+from django.conf import settings
+import urllib.parse
+
 def BASE_URL(request):
     """
     Return a BASE_URL template context for the current request.
     """
-    if request.is_secure():
-        scheme = 'https://'
-    else:
-        scheme = 'http://'
-    fullhost = request.get_host()
-    base = fullhost.split(":")[0]
-    return {'BASE_URL': scheme + base, }
+    parse = urllib.parse.urlparse(settings.BASE_URL)
+    return {'BASE_URL': parse.scheme+"://"+parse.netloc, }

web/models.py

@@ -10,7 +10,7 @@ def random_url():
 
 class Feed(models.Model):
     url = models.URLField(max_length=255)
-    element = models.CharField(max_length=255)
+    element = models.CharField(max_length=1000)
     title = models.CharField(max_length=255)
     content = models.CharField(max_length=255)
     date = models.CharField(max_length=255)
@@ -18,4 +18,4 @@ class Feed(models.Model):
     link = models.CharField(max_length=255)
     creation_date = models.DateTimeField(auto_now=True)
 
-    uurl = models.CharField(max_length=18, default=random_url, unique=True)
+    uurl = models.CharField(max_length=18, default=random_url, unique=True)

web/templates/feeds.html

@@ -19,7 +19,7 @@
 
                 <div id="collapse{{ feed.id }}" class="collapse" aria-labelledby="heading{{ feed.id }}" data-parent="#accordionExample">
                   <div class="card-body">
-                    <code>{{ BASE_URL }}/{{ feed.uurl }}.rss</code>
+                    <code>{{ BASE_URL }}{% url 'rss' uurl=feed.uurl %}</code>
                     <p><a class="btn btn-danger" href="{% url 'feed_delete' feed.id %}">Delete</a></p>
                   </div>
                 </div>

web/templates/homepage.html

@@ -5,7 +5,7 @@
         <div class="col-lg-12 text-center">
             <h1 class="mt-5">Generate RSS out of any website</h1>
             {% if error %}<div class="alert alert-danger" role="alert">{{ error }}</div>{% endif %}
-            <form action="/" method="post">
+            <form action="{% url 'homepage' %}" method="post">
                 {% csrf_token %}
                 <div class="form-group">
                     <input type="text" class="form-control" name="url" id="url" placeholder="http://" {% if url %}value="{{ url }}"{% endif %}>

web/templates/setup.html

@@ -29,7 +29,7 @@
                 <code style="display:block" id="link-selector"></code>
             </li>
             <li>
-                <form action="/newfeed" method="post">
+                <form action="{% url 'newfeed' %}" method="post">
                     {% csrf_token %}
                     <input type="hidden" id="url" name="url" value="{{ url }}">
                     <input type="hidden" id="element" name="element" value="">
@@ -44,7 +44,7 @@
         </ul>
     </div>
     <!-- /#sidebar-wrapper -->
-    <iframe id="preview" style="width:100%" src="/iframe/{{ url }}"></iframe>
+    <iframe id="preview" style="width:100%" src="{% url 'iframe' encodedurl=encodedurl %}"></iframe>
     <script>
         $(function() {
             function handleResize() {

web/templates/template.html

@@ -26,14 +26,14 @@
     <!-- Navigation -->
     <nav class="navbar navbar-expand-lg navbar-dark bg-dark static-top">
       <div class="container">
-        <a class="navbar-brand" href="/">HRSS</a>
+        <a class="navbar-brand" href="{% url 'homepage' %}">HRSS</a>
         <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarResponsive" aria-controls="navbarResponsive" aria-expanded="false" aria-label="Toggle navigation">
           <span class="navbar-toggler-icon"></span>
         </button>
         <div class="collapse navbar-collapse" id="navbarResponsive">
           <ul class="navbar-nav ml-auto">
             <li class="nav-item">
-              <a class="nav-link" href="/">New
+              <a class="nav-link" href="{% url 'homepage' %}">New
                 <span class="sr-only">(current)</span>
               </a>
             </li>

web/urls.py

@@ -3,8 +3,8 @@ from . import views
 
 urlpatterns = [
     url(r'^$', views.homepage, name='homepage'),
-    url(r'^iframe/(?P<url>.+)$', views.iframe, name='iframe'),
-    url(r'^setup/(?P<url>.+)$', views.setup, name='setup'),
+    url(r'^iframe/(?P<encodedurl>.+)$', views.iframe, name='iframe'),
+    url(r'^setup/(?P<encodedurl>.+)$', views.setup, name='setup'),
     url(r'^newfeed$', views.newfeed, name='newfeed'),
     url(r'^feeds$', views.feeds, name='feeds'),
     url(r'^feeds/delete/(?P<id>[0-9]+)$', views.feed_delete, name='feed_delete'),

web/utils.py

@@ -2,20 +2,25 @@ import requests
 from django.core.validators import URLValidator
 from django.core.exceptions import ValidationError
 from requests.exceptions import RequestException
-
 from bs4 import BeautifulSoup
+import logging
 
+logger = logging.getLogger(__name__)
+
+def get_url(url):
+    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:63.0) Gecko/20100101 Firefox/63.0"}
+    return requests.get(url, headers=headers)
 
 def is_valid_url(url):
     try:
         URLValidator()(url)
-        requests.get(url).raise_for_status()
+        get_url(url).raise_for_status()
         return True
     except ValidationError as e:
-        print(url+" is not a valid url")
+        logger.debug(url+" is not a valid url")
         return False
     except RequestException as e:
-        print(url+" led to exception: "+str(e))
+        logger.debug(url+" led to exception: "+str(e))
         return False
 
 
@@ -23,24 +28,34 @@ def find_longest_common_string(s1, s2):
     from difflib import SequenceMatcher
 
     match = SequenceMatcher(None, s1, s2).find_longest_match(0, len(s1), 0, len(s2))
-    return s1[match.a: match.a + match.size]  # -> apple pie
+    return s1[match.a: match.a + match.size]
+
 
 def fetch_feed(feed, limit=10):
+    logger.debug("Fetching feed "+feed.url)
     items=[]
-    rep = requests.get(feed.url).text
-    soup = BeautifulSoup(rep)
-    elements = soup.select(feed.element)
+    rep = get_url(feed.url).text
+    soup = BeautifulSoup(rep, "html5lib")
+    try:
+        elements = soup.select(feed.element)
+    except Exception as e:
+        logger.debug("Error while fetching elements ("+feed.element+"): "+str(e))
+        return False
+    logger.debug("Found "+str(len(elements))+" news")
     for element in elements:
         if len(items) >= limit:
             break
-
+        logger.debug("Title ("+feed.element+ " > "+feed.title+")")
         try:
             title = element.select(feed.title)[0].text
-        except Exception:
+            logger.debug("Match title "+title)
+        except Exception as e:
+            logger.debug("Error while selecting feed title: "+str(e))
             return False
         try:
             content = element.select(feed.content)[0].text
-        except Exception:
+        except Exception as e:
+            logger.debug("Error while selecting content: "+str(e))
             return False
         try:
             date = element.select(feed.date)[0].text
@@ -52,6 +67,12 @@ def fetch_feed(feed, limit=10):
             author = False
         try:
             link = element.select(feed.link)[0]["href"]
+            if link and len(link) > 2 and link[0] == "/" and link[1] != "/":
+                # fixes issue #5 with relative link
+                # prepend base url
+                base_scheme = feed.url.split("://")[0]
+                base_url = feed.url.split("//")[-1].split("/")[0].split('?')[0]
+                link = base_scheme + "://" + base_url + link
         except Exception:
             link = False
         items.append({"title": title, "content": content, "pubDate": date, "author": author, "link": link})

web/views.py

@@ -4,22 +4,30 @@ from .utils import *
 from .models import Feed
 from django.db.models import ObjectDoesNotExist
 from bs4 import BeautifulSoup
+import logging
+from urllib.parse import quote_plus, unquote_plus
+import traceback
+import sys
 # Create your views here.
 
+logger = logging.getLogger(__name__)
 
-def iframe(request, url):
-    content_type = False
+def iframe(request, encodedurl):
+    sys.setrecursionlimit(10000)
     try:
-        req = requests.get(url)
+        url = unquote_plus(encodedurl)
+        req = get_url(url)
         html = req.content
         bs = False
 
         content_type = req.headers["Content-Type"] if "Content-Type" in req.headers else False
 
         if not content_type or content_type.startswith("text/html"):
+            logger.debug("No content-type or content-type ~= '^text/html'")
             bs = BeautifulSoup(html, 'html.parser')
             base_scheme = url.split("://")[0]
             base_url = url.split("//")[-1].split("/")[0].split('?')[0]
+            logger.debug("URL: "+base_scheme+"://"+base_url)
 
             # fixes
             # fix click links
@@ -33,6 +41,11 @@ def iframe(request, url):
                 if link["href"].startswith("/"):
                     link["href"] = "/iframe/" + base_scheme + "://" + base_url + link["href"]
 
+            # test: remove js
+            all_scripts = bs.find_all("script")
+            for script in all_scripts:
+                script.extract()
+
             # fix absolute javascript
             all_scripts = bs.find_all("script", {"src": True})
             for script in all_scripts:
@@ -48,32 +61,37 @@ def iframe(request, url):
         html = final_html
 
     except Exception as e:
-        html = str(e)
+        traceback.print_exc()
+        return HttpResponse("An error has occured", content_type=500)
     return HttpResponse(html, content_type=content_type)
 
+
 def dummy(request):
     return HttpResponse("toto")
 
+
 def homepage(request):
     if request.method == 'POST':
         if "url" in request.POST and request.POST["url"]:
             url = request.POST["url"]
             if is_valid_url(url):
-                return redirect("/setup/"+url)
+                return redirect("setup", encodedurl=quote_plus(url))
             else:
                 return render(request, 'homepage.html', {"url": url, "error": url+" is not a valid URL."})
     return render(request, 'homepage.html')
 
-def setup(request, url):
-    if is_valid_url(url):
-        return render(request, 'setup.html', {"url": url})
+
+def setup(request, encodedurl):
+    decoded_url = unquote_plus(encodedurl)
+    if is_valid_url(decoded_url):
+        return render(request, 'setup.html', {"encodedurl": encodedurl, "url": decoded_url})
     else:
-        return redirect("/")
+        return redirect("homepage")
 
 
 def newfeed(request):
     if request.method == 'POST':
-        if not "url" in request.POST or not "element" in request.POST or not "title" in request.POST or not "content" in request.POST:
+        if not "url" in request.POST or not request.POST["url"] or not "element" in request.POST or not request.POST["element"] or not "title" in request.POST or not request.POST["title"] or not "content" in request.POST or not request.POST["content"]:
             return HttpResponse("Error, missing required element")
         url = request.POST["url"]
         element = request.POST["element"]
@@ -101,9 +119,9 @@ def newfeed(request):
         feed = Feed(url=url, element=element, title=title, content=content, date=date, author=author, link=link)
         feed.save()
 
-        return redirect("/feeds")
+        return redirect("feeds")
     else:
-        return redirect("/")
+        return redirect("homepage")
 
 def feeds(request):
     feeds = Feed.objects.all()
@@ -111,15 +129,22 @@ def feeds(request):
 
 def feed_delete(request, id):
     try:
-        Feed.objects.get(pk=id).delete()
-    except Exception as e:
-        pass
-    finally:
-        return redirect("/feeds")
+        # demo website: disable deleting feeds
+        if not request.get_host() == "hrss.hipstercat.fr:443":
+            Feed.objects.get(pk=id).delete()
+            logger.info("Removed feed ID "+id)
+            return redirect("feeds")
+        else:
+            return HttpResponse("Deleting is disabled on demo website.", status=403)
+    except ObjectDoesNotExist:
+        return redirect("feeds")
 
 def rss(request, uurl):
     try:
         feed = Feed.objects.get(uurl=uurl)
-        return render(request, "feed.xml", {"feed": feed, "rss": fetch_feed(feed)}, content_type="application/rss+xml")
+        fetched = fetch_feed(feed)
+        if not fetched or not fetched["items"]:
+            return HttpResponse("Error: feed is empty. Did you set up 'element' field correctly?", status=422)
+        return render(request, "feed.xml", {"feed": feed, "rss": fetched}, content_type="application/rss+xml")
     except ObjectDoesNotExist:
-        return HttpResponse("nope")
+        return HttpResponse("Error: feed is unknown", status=404)