summaryrefslogtreecommitdiff
path: root/feedgenerator/django/utils/feedgenerator.py
blob: b5d858c0a032bf33b3b14ca66225c46507a6feab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
"""
Syndication feed generation library -- used for generating RSS, etc.

Sample usage:

>>> from django.utils import feedgenerator
>>> feed = feedgenerator.Rss201rev2Feed(
...     title="Poynter E-Media Tidbits",
...     link="http://www.poynter.org/column.asp?id=31",
...     description="A group Weblog by the sharpest minds in online media/journalism/publishing.",
...     language="en",
... )
>>> feed.add_item(
...     title="Hello",
...     link="http://www.holovaty.com/test/",
...     description="Testing."
... )
>>> with open('test.rss', 'w') as fp:
...     feed.write(fp, 'utf-8')

For definitions of the different versions of RSS, see:
http://web.archive.org/web/20110718035220/http://diveintomark.org/archives/2004/02/04/incompatible-rss
"""
import datetime
from urllib.parse import urlparse
from .xmlutils import SimplerXMLGenerator
from .encoding import force_text, iri_to_uri
from . import datetime_safe
from io import StringIO
from .timezone import is_aware

def rfc2822_date(date):
    # We can't use strftime() because it produces locale-dependent results, so
    # we have to map english month and day names manually
    months = ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec',)
    days = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
    # Support datetime objects older than 1900
    date = datetime_safe.new_datetime(date)
    # We do this ourselves to be timezone aware, email.Utils is not tz aware.
    dow = days[date.weekday()]
    month = months[date.month - 1]
    time_str = date.strftime(f'{dow}, %d {month} %Y %H:%M:%S ')
    if is_aware(date):
        offset = date.tzinfo.utcoffset(date)
        timezone = (offset.days * 24 * 60) + (offset.seconds // 60)
        hour, minute = divmod(timezone, 60)
        return time_str + '%+03d%02d' % (hour, minute)
    else:
        return time_str + '-0000'

def rfc3339_date(date):
    # Support datetime objects older than 1900
    date = datetime_safe.new_datetime(date)
    time_str = date.strftime('%Y-%m-%dT%H:%M:%S')
    if is_aware(date):
        offset = date.tzinfo.utcoffset(date)
        timezone = (offset.days * 24 * 60) + (offset.seconds // 60)
        hour, minute = divmod(timezone, 60)
        return time_str + '%+03d:%02d' % (hour, minute)
    else:
        return time_str + 'Z'

def get_tag_uri(url, date):
    """
    Creates a TagURI.

    See http://web.archive.org/web/20110514113830/http://diveintomark.org/archives/2004/05/28/howto-atom-id
    """
    bits = urlparse(url)
    d = ''
    if date is not None:
        d = ',%s' % datetime_safe.new_datetime(date).strftime('%Y-%m-%d')
    fragment = ''
    if bits.fragment != '':
        fragment = '/%s' % (bits.fragment)
    return f'tag:{bits.hostname}{d}:{bits.path}{fragment}'

class SyndicationFeed:
    "Base class for all syndication feeds. Subclasses should provide write()"
    def __init__(self, title, link, description, language=None, author_email=None,
            author_name=None, author_link=None, subtitle=None, categories=None,
            feed_url=None, feed_copyright=None, feed_guid=None, ttl=None, **kwargs):
        to_unicode = lambda s: force_text(s, strings_only=True)
        if categories:
            categories = [force_text(c) for c in categories]
        if ttl is not None:
            # Force ints to unicode
            ttl = force_text(ttl)
        self.feed = {
            'title': to_unicode(title),
            'link': iri_to_uri(link),
            'description': to_unicode(description),
            'language': to_unicode(language),
            'author_email': to_unicode(author_email),
            'author_name': to_unicode(author_name),
            'author_link': iri_to_uri(author_link),
            'subtitle': to_unicode(subtitle),
            'categories': categories or (),
            'feed_url': iri_to_uri(feed_url),
            'feed_copyright': to_unicode(feed_copyright),
            'id': feed_guid or link,
            'ttl': ttl,
        }
        self.feed.update(kwargs)
        self.items = []

    def add_item(self, title, link, description, author_email=None,
        author_name=None, author_link=None, pubdate=None, comments=None,
        unique_id=None, enclosure=None, categories=(), item_copyright=None,
        ttl=None, content=None, updateddate=None, **kwargs):
        """
        Adds an item to the feed. All args are expected to be Python Unicode
        objects except pubdate and updateddate, which are datetime.datetime
        objects, and enclosure, which is an instance of the Enclosure class.
        """
        to_unicode = lambda s: force_text(s, strings_only=True)
        if categories:
            categories = [to_unicode(c) for c in categories]
        if ttl is not None:
            # Force ints to unicode
            ttl = force_text(ttl)
        item = {
            'title': to_unicode(title),
            'link': iri_to_uri(link),
            'description': to_unicode(description),
            'content': to_unicode(content),
            'author_email': to_unicode(author_email),
            'author_name': to_unicode(author_name),
            'author_link': iri_to_uri(author_link),
            'pubdate': pubdate,
            'updateddate': updateddate,
            'comments': to_unicode(comments),
            'unique_id': to_unicode(unique_id),
            'enclosure': enclosure,
            'categories': categories or (),
            'item_copyright': to_unicode(item_copyright),
            'ttl': ttl,
        }
        item.update(kwargs)
        self.items.append(item)

    def num_items(self):
        return len(self.items)

    def root_attributes(self):
        """
        Return extra attributes to place on the root (i.e. feed/channel) element.
        Called from write().
        """
        return {}

    def add_root_elements(self, handler):
        """
        Add elements in the root (i.e. feed/channel) element. Called
        from write().
        """
        pass

    def item_attributes(self, item):
        """
        Return extra attributes to place on each item (i.e. item/entry) element.
        """
        return {}

    def add_item_elements(self, handler, item):
        """
        Add elements on each item (i.e. item/entry) element.
        """
        pass

    def write(self, outfile, encoding):
        """
        Outputs the feed in the given encoding to outfile, which is a file-like
        object. Subclasses should override this.
        """
        raise NotImplementedError

    def writeString(self, encoding):
        """
        Returns the feed in the given encoding as a string.
        """
        s = StringIO()
        self.write(s, encoding)
        return s.getvalue()

    def latest_post_date(self):
        """
        Returns the latest item's pubdate or updateddate. If no item has either
        date, returns the current date/time.
        """
        updates = [i['pubdate'] for i in self.items if i['pubdate'] is not None]
        updates.extend(i['updateddate'] for i in self.items if i['updateddate'] is not None)
        if len(updates) > 0:
            updates.sort()
            return updates[-1]
        else:
            return datetime.datetime.now()

class Enclosure:
    "Represents an RSS enclosure"
    def __init__(self, url, length, mime_type):
        "All args are expected to be Python Unicode objects"
        self.length, self.mime_type = length, mime_type
        self.url = iri_to_uri(url)

class RssFeed(SyndicationFeed):
    mime_type = 'application/rss+xml; charset=utf-8'
    def write(self, outfile, encoding):
        handler = SimplerXMLGenerator(outfile, encoding)
        handler.startDocument()
        handler.startElement("rss", self.rss_attributes())
        handler.startElement("channel", self.root_attributes())
        self.add_root_elements(handler)
        self.write_items(handler)
        self.endChannelElement(handler)
        handler.endElement("rss")

    def rss_attributes(self):
        return {'version': self._version}

    def write_items(self, handler):
        for item in self.items:
            handler.startElement('item', self.item_attributes(item))
            self.add_item_elements(handler, item)
            handler.endElement("item")

    def add_root_elements(self, handler):
        # Required Elements as per the specification
        handler.addQuickElement("title", self.feed['title'])
        handler.addQuickElement("link", self.feed['link'])
        handler.addQuickElement("description", self.feed['description'])

        # Optional Channel Elements
        if self.feed['language'] is not None:
            handler.addQuickElement("language", self.feed['language'])
        for cat in self.feed['categories']:
            handler.addQuickElement("category", cat)
        if self.feed['feed_copyright'] is not None:
            handler.addQuickElement("copyright", self.feed['feed_copyright'])
        handler.addQuickElement("lastBuildDate", rfc2822_date(self.latest_post_date()))
        if self.feed['ttl'] is not None:
            handler.addQuickElement("ttl", self.feed['ttl'])

    def endChannelElement(self, handler):
        handler.endElement("channel")

class RssUserland091Feed(RssFeed):
    _version = "0.91"
    def add_item_elements(self, handler, item):
        handler.addQuickElement("title", item['title'])
        handler.addQuickElement("link", item['link'])
        if item['description'] is not None:
            handler.addQuickElement("description", item['description'])

class Rss201rev2Feed(RssFeed):
    # Spec: http://blogs.law.harvard.edu/tech/rss
    _version = "2.0"
    def add_item_elements(self, handler, item):
        handler.addQuickElement("title", item['title'])
        handler.addQuickElement("link", item['link'])
        if item['description'] is not None:
            handler.addQuickElement("description", item['description'])

        # Author information.
        if item["author_name"] and item["author_email"]:
            handler.addQuickElement("author", "%s (%s)" % \
                (item['author_email'], item['author_name']))
        elif item["author_email"]:
            handler.addQuickElement("author", item["author_email"])
        elif item["author_name"]:
            handler.addQuickElement("dc:creator", item["author_name"], {"xmlns:dc": "http://purl.org/dc/elements/1.1/"})

        if item['pubdate'] is not None:
            handler.addQuickElement("pubDate", rfc2822_date(item['pubdate']))
        if item['comments'] is not None:
            handler.addQuickElement("comments", item['comments'])
        if item['unique_id'] is not None:
            handler.addQuickElement("guid", item['unique_id'], attrs={'isPermaLink': 'false'})
        if item['ttl'] is not None:
            handler.addQuickElement("ttl", item['ttl'])

        # Enclosure.
        if item['enclosure'] is not None:
            handler.addQuickElement("enclosure", '',
                {"url": item['enclosure'].url, "length": item['enclosure'].length,
                    "type": item['enclosure'].mime_type})

        # Categories.
        for cat in item['categories']:
            handler.addQuickElement("category", cat)

class Atom1Feed(SyndicationFeed):
    # Spec: http://atompub.org/2005/07/11/draft-ietf-atompub-format-10.html
    mime_type = 'application/atom+xml; charset=utf-8'
    ns = "http://www.w3.org/2005/Atom"

    def write(self, outfile, encoding):
        handler = SimplerXMLGenerator(outfile, encoding)
        handler.startDocument()
        handler.startElement('feed', self.root_attributes())
        self.add_root_elements(handler)
        self.write_items(handler)
        handler.endElement("feed")

    def root_attributes(self):
        if self.feed['language'] is not None:
            return {"xmlns": self.ns, "xml:lang": self.feed['language']}
        else:
            return {"xmlns": self.ns}

    def add_root_elements(self, handler):
        handler.addQuickElement("title", self.feed['title'])
        handler.addQuickElement("link", "", {"rel": "alternate", "href": self.feed['link']})
        if self.feed['feed_url'] is not None:
            handler.addQuickElement("link", "", {"rel": "self", "href": self.feed['feed_url']})
        handler.addQuickElement("id", self.feed['id'])
        handler.addQuickElement("updated", rfc3339_date(self.latest_post_date()))
        if self.feed['author_name'] is not None:
            handler.startElement("author", {})
            handler.addQuickElement("name", self.feed['author_name'])
            if self.feed['author_email'] is not None:
                handler.addQuickElement("email", self.feed['author_email'])
            if self.feed['author_link'] is not None:
                handler.addQuickElement("uri", self.feed['author_link'])
            handler.endElement("author")
        # try to use description or subtitle if provided, subtitle has
        # precedence above description
        if self.feed['description'] is not None:
            handler.addQuickElement("subtitle", self.feed['description'])
        if self.feed['subtitle'] is not None:
            handler.addQuickElement("subtitle", self.feed['subtitle'])
        for cat in self.feed['categories']:
            handler.addQuickElement("category", "", {"term": cat})
        if self.feed['feed_copyright'] is not None:
            handler.addQuickElement("rights", self.feed['feed_copyright'])

    def write_items(self, handler):
        for item in self.items:
            handler.startElement("entry", self.item_attributes(item))
            self.add_item_elements(handler, item)
            handler.endElement("entry")

    def add_item_elements(self, handler, item):
        handler.addQuickElement("title", item['title'])
        handler.addQuickElement("link", "", {"href": item['link'], "rel": "alternate"})

        updateddate = datetime.datetime.now()
        if item['pubdate'] is not None:
            handler.addQuickElement("published", rfc3339_date(item['pubdate']))
            updateddate = item['pubdate']
        if item['updateddate'] is not None:
            updateddate = item['updateddate']
        handler.addQuickElement("updated", rfc3339_date(updateddate))

        # Author information.
        if item['author_name'] is not None:
            handler.startElement("author", {})
            handler.addQuickElement("name", item['author_name'])
            if item['author_email'] is not None:
                handler.addQuickElement("email", item['author_email'])
            if item['author_link'] is not None:
                handler.addQuickElement("uri", item['author_link'])
            handler.endElement("author")

        # Unique ID.
        if item['unique_id'] is not None:
            unique_id = item['unique_id']
        else:
            unique_id = get_tag_uri(item['link'], item['pubdate'])
        handler.addQuickElement("id", unique_id)

        # Summary.
        if item['description'] is not None:
            handler.addQuickElement("summary", item['description'], {"type": "html"})

        # Full content.
        if item['content'] is not None:
            handler.addQuickElement("content", item['content'], {"type": "html"})

        # Enclosure.
        if item['enclosure'] is not None:
            handler.addQuickElement("link", '',
                {"rel": "enclosure",
                 "href": item['enclosure'].url,
                 "length": item['enclosure'].length,
                 "type": item['enclosure'].mime_type})

        # Categories.
        for cat in item['categories']:
            handler.addQuickElement("category", "", {"term": cat})

        # Rights.
        if item['item_copyright'] is not None:
            handler.addQuickElement("rights", item['item_copyright'])

# This isolates the decision of what the system default is, so calling code can
# do "feedgenerator.DefaultFeed" instead of "feedgenerator.Rss201rev2Feed".
DefaultFeed = Rss201rev2Feed