summary refs log tree commit diff
path: root/synapse/rest/media/v1/oembed.py
blob: 6d7e1f9064af34b6bccdafd98215502e7a2d5fd8 (plain) (blame)
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
#  Copyright 2021 The Matrix.org Foundation C.I.C.
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.
import logging
import urllib.parse
from typing import TYPE_CHECKING, List, Optional

import attr

from synapse.http.client import SimpleHttpClient
from synapse.types import JsonDict
from synapse.util import json_decoder

if TYPE_CHECKING:
    from lxml import etree

    from synapse.server import HomeServer

logger = logging.getLogger(__name__)


@attr.s(slots=True, frozen=True, auto_attribs=True)
class OEmbedResult:
    # The Open Graph result (converted from the oEmbed result).
    open_graph_result: JsonDict
    # Number of milliseconds to cache the content, according to the oEmbed response.
    #
    # This will be None if no cache-age is provided in the oEmbed response (or
    # if the oEmbed response cannot be turned into an Open Graph response).
    cache_age: Optional[int]


class OEmbedProvider:
    """
    A helper for accessing oEmbed content.

    It can be used to check if a URL should be accessed via oEmbed and for
    requesting/parsing oEmbed content.
    """

    def __init__(self, hs: "HomeServer", client: SimpleHttpClient):
        self._oembed_patterns = {}
        for oembed_endpoint in hs.config.oembed.oembed_patterns:
            api_endpoint = oembed_endpoint.api_endpoint

            # Only JSON is supported at the moment. This could be declared in
            # the formats field. Otherwise, if the endpoint ends in .xml assume
            # it doesn't support JSON.
            if (
                oembed_endpoint.formats is not None
                and "json" not in oembed_endpoint.formats
            ) or api_endpoint.endswith(".xml"):
                logger.info(
                    "Ignoring oEmbed endpoint due to not supporting JSON: %s",
                    api_endpoint,
                )
                continue

            # Iterate through each URL pattern and point it to the endpoint.
            for pattern in oembed_endpoint.url_patterns:
                self._oembed_patterns[pattern] = api_endpoint
        self._client = client

    def get_oembed_url(self, url: str) -> Optional[str]:
        """
        Check whether the URL should be downloaded as oEmbed content instead.

        Args:
            url: The URL to check.

        Returns:
            A URL to use instead or None if the original URL should be used.
        """
        for url_pattern, endpoint in self._oembed_patterns.items():
            if url_pattern.fullmatch(url):
                # TODO Specify max height / width.

                # Note that only the JSON format is supported, some endpoints want
                # this in the URL, others want it as an argument.
                endpoint = endpoint.replace("{format}", "json")

                args = {"url": url, "format": "json"}
                query_str = urllib.parse.urlencode(args, True)
                return f"{endpoint}?{query_str}"

        # No match.
        return None

    def autodiscover_from_html(self, tree: "etree.Element") -> Optional[str]:
        """
        Search an HTML document for oEmbed autodiscovery information.

        Args:
            tree: The parsed HTML body.

        Returns:
            The URL to use for oEmbed information, or None if no URL was found.
        """
        # Search for link elements with the proper rel and type attributes.
        for tag in tree.xpath(
            "//link[@rel='alternate'][@type='application/json+oembed']"
        ):
            if "href" in tag.attrib:
                return tag.attrib["href"]

        # Some providers (e.g. Flickr) use alternative instead of alternate.
        for tag in tree.xpath(
            "//link[@rel='alternative'][@type='application/json+oembed']"
        ):
            if "href" in tag.attrib:
                return tag.attrib["href"]

        return None

    def parse_oembed_response(self, url: str, raw_body: bytes) -> OEmbedResult:
        """
        Parse the oEmbed response into an Open Graph response.

        Args:
            url: The URL which is being previewed (not the one which was
                requested).
            raw_body: The oEmbed response as JSON encoded as bytes.

        Returns:
            json-encoded Open Graph data
        """

        try:
            # oEmbed responses *must* be UTF-8 according to the spec.
            oembed = json_decoder.decode(raw_body.decode("utf-8"))

            # Ensure there's a version of 1.0.
            oembed_version = oembed["version"]
            if oembed_version != "1.0":
                raise RuntimeError(f"Invalid version: {oembed_version}")

            # Ensure the cache age is None or an int.
            cache_age = oembed.get("cache_age")
            if cache_age:
                cache_age = int(cache_age) * 1000

            # The results.
            open_graph_response = {
                "og:url": url,
            }

            # Use either title or author's name as the title.
            title = oembed.get("title") or oembed.get("author_name")
            if title:
                open_graph_response["og:title"] = title

            # Use the provider name and as the site.
            provider_name = oembed.get("provider_name")
            if provider_name:
                open_graph_response["og:site_name"] = provider_name

            # If a thumbnail exists, use it. Note that dimensions will be calculated later.
            if "thumbnail_url" in oembed:
                open_graph_response["og:image"] = oembed["thumbnail_url"]

            # Process each type separately.
            oembed_type = oembed["type"]
            if oembed_type == "rich":
                calc_description_and_urls(open_graph_response, oembed["html"])

            elif oembed_type == "photo":
                # If this is a photo, use the full image, not the thumbnail.
                open_graph_response["og:image"] = oembed["url"]

            elif oembed_type == "video":
                open_graph_response["og:type"] = "video.other"
                calc_description_and_urls(open_graph_response, oembed["html"])
                open_graph_response["og:video:width"] = oembed["width"]
                open_graph_response["og:video:height"] = oembed["height"]

            elif oembed_type == "link":
                open_graph_response["og:type"] = "website"

            else:
                raise RuntimeError(f"Unknown oEmbed type: {oembed_type}")

        except Exception as e:
            # Trap any exception and let the code follow as usual.
            logger.warning(f"Error parsing oEmbed metadata from {url}: {e:r}")
            open_graph_response = {}
            cache_age = None

        return OEmbedResult(open_graph_response, cache_age)


def _fetch_urls(tree: "etree.Element", tag_name: str) -> List[str]:
    results = []
    for tag in tree.xpath("//*/" + tag_name):
        if "src" in tag.attrib:
            results.append(tag.attrib["src"])
    return results


def calc_description_and_urls(open_graph_response: JsonDict, html_body: str) -> None:
    """
    Calculate description for an HTML document.

    This uses lxml to convert the HTML document into plaintext. If errors
    occur during processing of the document, an empty response is returned.

    Args:
        open_graph_response: The current Open Graph summary. This is updated with additional fields.
        html_body: The HTML document, as bytes.

    Returns:
        The summary
    """
    # If there's no body, nothing useful is going to be found.
    if not html_body:
        return

    from lxml import etree

    # Create an HTML parser. If this fails, log and return no metadata.
    parser = etree.HTMLParser(recover=True, encoding="utf-8")

    # Attempt to parse the body. If this fails, log and return no metadata.
    tree = etree.fromstring(html_body, parser)

    # The data was successfully parsed, but no tree was found.
    if tree is None:
        return

    # Attempt to find interesting URLs (images, videos, embeds).
    if "og:image" not in open_graph_response:
        image_urls = _fetch_urls(tree, "img")
        if image_urls:
            open_graph_response["og:image"] = image_urls[0]

    video_urls = _fetch_urls(tree, "video") + _fetch_urls(tree, "embed")
    if video_urls:
        open_graph_response["og:video"] = video_urls[0]

    from synapse.rest.media.v1.preview_url_resource import _calc_description

    description = _calc_description(tree)
    if description:
        open_graph_response["og:description"] = description