Merge pull request #96 from cthulahoops/goodreads_import

Goodreads import

fedireads/connectors/abstract_connector.py

@@ -53,8 +53,12 @@ class AbstractConnector(ABC):
 
 class SearchResult(object):
     ''' standardized search result object '''
-    def __init__(self, title, key, author, year):
+    def __init__(self, title, key, author, year, raw_data):
         self.title = title
         self.key = key
         self.author = author
         self.year = year
+        self.raw_data = raw_data
+
+    def __repr__(self):
+        return "<SearchResult key={!r} title={!r} author={!r}>".format(self.key, self.title, self.author)

fedireads/connectors/openlibrary.py

@@ -31,6 +31,7 @@ class OpenLibraryConnector(AbstractConnector):
                 key,
                 author[0],
                 doc.get('first_publish_year'),
+                doc
             ))
         return results
 

fedireads/forms.py

@@ -1,6 +1,7 @@
 ''' usin django model forms '''
 from django.core.validators import MaxValueValidator, MinValueValidator
 from django.forms import ModelForm, PasswordInput, IntegerField
+from django import forms
 
 from fedireads import models
 
@@ -73,3 +74,6 @@ class TagForm(ModelForm):
         help_texts = {f: None for f in fields}
         labels = {'name': 'Add a tag'}
 
+
+class ImportForm(forms.Form):
+    csv_file = forms.FileField()

fedireads/goodreads_import.py

@@ -0,0 +1,75 @@
+import re
+import csv
+import itertools
+from requests import HTTPError
+
+from fedireads import books_manager
+
+# Mapping goodreads -> fedireads shelf titles.
+GOODREADS_SHELVES = {
+        'read': 'read',
+        'currently-reading': 'reading',
+        'to-read': 'to-read',
+}
+MAX_ENTRIES = 20
+
+def unquote_string(text):
+    match = re.match(r'="([^"]*)"', text)
+    if match:
+        return match.group(1)
+    else:
+        return text
+
+def construct_search_term(title, author):
+    # Strip brackets (usually series title from search term)
+    title = re.sub(r'\s*\([^)]*\)\s*', '', title)
+    # Open library doesn't like including author initials in search term.
+    author = re.sub(r'(\w\.)+\s*', '', author)
+
+    return ' '.join([title, author])
+
+class GoodreadsCsv(object):
+    def __init__(self, csv_file):
+        self.reader = csv.DictReader(csv_file)
+
+    def __iter__(self):
+        for line in itertools.islice(self.reader, MAX_ENTRIES):
+            entry = GoodreadsItem(line)
+            try:
+                entry.resolve()
+            except HTTPError:
+                pass
+            yield entry
+
+class GoodreadsItem(object):
+    def __init__(self, line):
+        self.line = line
+        self.book = None
+
+    def resolve(self):
+        self.book = self.get_book_from_isbn()
+        if not self.book:
+            self.book = self.get_book_from_title_author()
+
+    def get_book_from_isbn(self):
+        isbn = unquote_string(self.line['ISBN13'])
+        search_results = books_manager.search(isbn)
+        if search_results:
+            return books_manager.get_or_create_book(search_results[0].key)
+
+    def get_book_from_title_author(self):
+        search_term = construct_search_term(self.line['Title'], self.line['Author'])
+        search_results = books_manager.search(search_term)
+        if search_results:
+            return books_manager.get_or_create_book(search_results[0].key)
+
+    @property
+    def shelf(self):
+        if self.line['Exclusive Shelf']:
+            return GOODREADS_SHELVES[self.line['Exclusive Shelf']]
+
+    def __repr__(self):
+        return "<GoodreadsItem {!r}>".format(self.line['Title'])
+
+    def __str__(self):
+        return "{} by {}".format(self.line['Title'], self.line['Author'])

fedireads/models/book.py

@@ -54,6 +54,9 @@ class Book(FedireadsModel):
         model_name = type(self).__name__.lower()
         return '%s/%s/%s' % (base_path, model_name, self.openlibrary_key)
 
+    def __repr__(self):
+        return "<{} key={!r} title={!r} author={!r}>".format(self.__class__, self.openlibrary_key, self.title, self.author)
+
 
 class Work(Book):
     ''' a work (an abstract concept of a book that manifests in an edition) '''

fedireads/outgoing.py

@@ -157,6 +157,31 @@ def handle_unshelve(user, book, shelf):
     broadcast(user, activity, recipients)
 
 
+def handle_import_books(user, items):
+    new_books = []
+    for item in items:
+        if item.shelf:
+            desired_shelf = models.Shelf.objects.get(
+                identifier=item.shelf,
+                user=user
+            )
+            shelf, created = models.ShelfBook.objects.get_or_create(book=item.book, shelf=desired_shelf, added_by=user)
+            if created:
+                new_books.append(item.book)
+                activity = activitypub.get_add(user, item.book, desired_shelf)
+                recipients = get_recipients(user, 'public')
+                broadcast(user, activity, recipients)
+
+    if new_books:
+        message = 'imported {} books'.format(len(new_books))
+        status = create_status(user, message, mention_books=new_books)
+        status.status_type = 'Update'
+        status.save()
+
+        create_activity = activitypub.get_create(user, activitypub.get_status(status))
+        broadcast(user, create_activity, get_recipients(user, 'public'))
+
+
 def handle_review(user, book, name, content, rating):
     ''' post a review '''
     # validated and saves the review in the database so it has an id

fedireads/templates/import.html

@@ -0,0 +1,10 @@
+{% extends 'layout.html' %}
+{% block content %}
+<div id="content">
+    <form name="import" action="/import_data/" method="post" enctype="multipart/form-data">
+        {% csrf_token %}
+        {{ import_form.as_p }}
+        <button type="submit">Import</button>
+    </form>
+</div>
+{% endblock %}

fedireads/templates/import_results.html

@@ -0,0 +1,18 @@
+{% extends 'layout.html' %}
+{% block content %}
+<div id="content">
+    <div>
+        <h1>The following books could not be imported: </h1>
+
+        <ul>
+        {% for item in failures %}
+            <li>
+            {{ item }}
+            </li>
+        {% endfor %}
+        </ul>
+
+        <p>{{ success_count }} books imported successfully</p>
+    </div>
+</div>
+{% endblock %}

fedireads/templates/layout.html

@@ -31,6 +31,7 @@
             {% endif %}
             <li><a href="/#feed">Updates</a></li>
             <li><a href="/books">Discover Books</a></li>
+            <li><a href="/import">Import Books</a><li>
         </ul>
 
         <div id="actions">

fedireads/templates/snippets/status.html

@@ -21,13 +21,15 @@
     </h2>
 
     {% if not hide_book and status.mention_books.count %}
+    {% for book in status.mention_books.all|slice:"0:3" %}
     <div class="book-preview">
         {% if status.status_type == 'Review' %}
-            {% include 'snippets/book.html' with book=status.mention_books.first %}
+            {% include 'snippets/book.html' with book=book %}
         {% else %}
-            {% include 'snippets/book.html' with book=status.mention_books.first description=True %}
+            {% include 'snippets/book.html' with book=book description=True %}
         {% endif %}
     </div>
+    {% endfor %}
     {% endif %}
     {% if not hide_book and status.book%}
     <div class="book-preview">

fedireads/urls.py

@@ -34,6 +34,7 @@ urlpatterns = [
     re_path(r'^(?P<tab>home|local|federated)/?$', views.home_tab),
     re_path(r'^notifications/?', views.notifications_page),
     re_path(r'books/?$', views.books_page),
+    re_path(r'import/?$', views.import_page),
 
     # should return a ui view or activitypub json blob as requested
     # users
@@ -81,5 +82,6 @@ urlpatterns = [
     re_path(r'^accept_follow_request/?$', actions.accept_follow_request),
     re_path(r'^delete_follow_request/?$', actions.delete_follow_request),
 
+    re_path(r'import_data', actions.import_data),
 
 ] + static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)

fedireads/view_actions.py

@@ -1,14 +1,16 @@
 ''' views for actions you can take in the application '''
+from io import TextIOWrapper
+
 from django.contrib.auth import authenticate, login, logout
 from django.contrib.auth.decorators import login_required
 from django.http import HttpResponseBadRequest
 from django.shortcuts import redirect
 from django.template.response import TemplateResponse
-import re
 
 from fedireads import forms, models, books_manager, outgoing
 from fedireads.settings import DOMAIN
 from fedireads.views import get_user_from_username
+from fedireads.goodreads_import import GoodreadsCsv
 
 
 def user_login(request):
@@ -288,4 +290,26 @@ def delete_follow_request(request):
 
     outgoing.handle_outgoing_reject(requester, request.user, follow_request)
     return redirect('/user/%s' % request.user.localname)
+    
+@login_required
+def import_data(request):
+    form = forms.ImportForm(request.POST, request.FILES)
+    if form.is_valid():
+        results = []
+        failures = []
+        for item in GoodreadsCsv(TextIOWrapper(request.FILES['csv_file'], encoding=request.encoding)):
+            if item.book:
+                results.append(item)
+            else:
+                failures.append(item)
 
+        outgoing.handle_import_books(request.user, results)
+        if failures:
+            return TemplateResponse(request, 'import_results.html', {
+                    'success_count': len(results),
+                    'failures': failures,
+                })
+        else:
+            return redirect('/')
+    else:
+        return HttpResponseBadRequest()

fedireads/views.py

@@ -108,6 +108,14 @@ def books_page(request):
     }
     return TemplateResponse(request, 'books.html', data)
 
+@login_required
+def import_page(request):
+    ''' import history from goodreads '''
+    return TemplateResponse(request, 'import.html', {
+        'import_form': forms.ImportForm(),
+    })
+
+
 
 def login_page(request):
     ''' authentication '''