add RSS feed output; closes #109

2024-10-18 23:24:12 +00:00 · 2024-10-18 23:24:12 +00:00 · 7ffd805a03
commit 7ffd805a03
parent a7e2a0c981
6 changed files with 181 additions and 4 deletions
--- a/README.md
+++ b/README.md
@ -47,6 +47,7 @@ turn almost any device into a file server with resumable uploads/downloads using
    * [file manager](#file-manager) - cut/paste, rename, and delete files/folders (if you have permission)
    * [shares](#shares) - share a file or folder by creating a temporary link
    * [batch rename](#batch-rename) - select some files and press `F2` to bring up the rename UI
+    * [rss feeds](#rss-feeds) - monitor a folder with your RSS reader
    * [media player](#media-player) - plays almost every audio format there is
        * [audio equalizer](#audio-equalizer) - and [dynamic range compressor](https://en.wikipedia.org/wiki/Dynamic_range_compression)
        * [fix unreliable playback on android](#fix-unreliable-playback-on-android) - due to phone / app settings
@ -845,6 +846,30 @@ or a mix of both:
 the metadata keys you can use in the format field are the ones in the file-browser table header (whatever is collected with `-mte` and `-mtp`)


+## rss feeds
+
+monitor a folder with your RSS reader  , optionally recursive
+
+must be enabled per-volume with volflag `rss` or globally with `--rss`
+
+the feed includes itunes metadata for use with podcast readers such as [AntennaPod](https://antennapod.org/)
+
+a feed example: https://cd.ocv.me/a/d2/d22/?rss&fext=mp3
+
+url parameters:
+
+* `pw=hunter2` for password auth
+* `recursive` to also include subfolders
+* `title=foo` changes the feed title (default: folder name)
+* `fext=mp3,opus` only include mp3 and opus files (default: all)
+* `nf=30` only show the first 30 results (default: 250)
+* `sort=m` sort by mtime (file last-modified), newest first (default)
+  * `u` = upload-time; NOTE: non-uploaded files have upload-time `0`
+  * `n` = filename
+  * `a` = filesize
+  * uppercase = reverse-sort; `M` = oldest file first
+
+
 ## media player

 plays almost every audio format there is  (if the server has FFmpeg installed for on-demand transcoding)
--- a/copyparty/main.py
+++ b/copyparty/main.py
@ -1357,6 +1357,14 @@ def add_transcoding(ap):
    ap2.add_argument("--ac-maxage", metavar="SEC", type=int, default=86400, help="delete cached transcode output after \033[33mSEC\033[0m seconds")


+def add_rss(ap):
+    ap2 = ap.add_argument_group('RSS options')
+    ap2.add_argument("--rss", action="store_true", help="enable RSS output (experimental)")
+    ap2.add_argument("--rss-nf", metavar="HITS", type=int, default=250, help="default number of files to return (url-param 'nf')")
+    ap2.add_argument("--rss-fext", metavar="E,E", type=u, default="", help="default list of file extensions to include (url-param 'fext'); blank=all")
+    ap2.add_argument("--rss-sort", metavar="ORD", type=u, default="m", help="default sort order (url-param 'sort'); [\033[32mm\033[0m]=last-modified [\033[32mu\033[0m]=upload-time [\033[32mn\033[0m]=filename [\033[32ms\033[0m]=filesize; Uppercase=oldest-first. Note that upload-time is 0 for non-uploaded files")
+
+
 def add_db_general(ap, hcores):
    noidx = APPLESAN_TXT if MACOS else ""
    ap2 = ap.add_argument_group('general db options')
@ -1526,6 +1534,7 @@ def run_argparse(
    add_db_metadata(ap)
    add_thumbnail(ap)
    add_transcoding(ap)
+    add_rss(ap)
    add_ftp(ap)
    add_webdav(ap)
    add_tftp(ap)
--- a/copyparty/cfg.py
+++ b/copyparty/cfg.py
@ -46,6 +46,7 @@ def vf_bmap() -> dict[str, str]:
        "og_no_head",
        "og_s_title",
        "rand",
+        "rss",
        "xdev",
        "xlink",
        "xvol",
--- a/copyparty/httpcli.py
+++ b/copyparty/httpcli.py
@ -131,6 +131,8 @@ LOGUES = [[0, ".prologue.html"], [1, ".epilogue.html"]]

 READMES = [[0, ["preadme.md", "PREADME.md"]], [1, ["readme.md", "README.md"]]]

+RSS_SORT = {"m": "mt", "u": "at", "n": "fn", "s": "sz"}
+

 class HttpCli(object):
    """
@ -1201,8 +1203,146 @@ class HttpCli(object):
        if "h" in self.uparam:
            return self.tx_mounts()

+        if "rss" in self.uparam:
+            return self.tx_rss()
+
        return self.tx_browser()

+    def tx_rss(self) -> bool:
+        if self.do_log:
+            self.log("RSS  %s @%s" % (self.req, self.uname))
+
+        if not self.can_read:
+            return self.tx_404()
+
+        vn = self.vn
+        if not vn.flags.get("rss"):
+            raise Pebkac(405, "RSS is disabled in server config")
+
+        rem = self.rem
+        idx = self.conn.get_u2idx()
+        if not idx or not hasattr(idx, "p_end"):
+            if not HAVE_SQLITE3:
+                raise Pebkac(500, "sqlite3 not found on server; rss is disabled")
+            raise Pebkac(500, "server busy, cannot generate rss; please retry in a bit")
+
+        uv = [rem]
+        if "recursive" in self.uparam:
+            uq = "up.rd like ?||'%'"
+        else:
+            uq = "up.rd == ?"
+
+        zs = str(self.uparam.get("fext", self.args.rss_fext))
+        if zs in ("True", "False"):
+            zs = ""
+        if zs:
+            zsl = []
+            for ext in zs.split(","):
+                zsl.append("+up.fn like '%.'||?")
+                uv.append(ext)
+            uq += " and ( %s )" % (" or ".join(zsl),)
+
+        zs1 = self.uparam.get("sort", self.args.rss_sort)
+        zs2 = zs1.lower()
+        zs = RSS_SORT.get(zs2)
+        if not zs:
+            raise Pebkac(400, "invalid sort key; must be m/u/n/s")
+
+        uq += " order by up." + zs
+        if zs1 == zs2:
+            uq += " desc"
+
+        nmax = int(self.uparam.get("nf") or self.args.rss_nf)
+
+        hits = idx.run_query(self.uname, [self.vn], uq, uv, False, False, nmax)[0]
+
+        pw = self.ouparam.get("pw")
+        if pw:
+            q_pw = "?pw=%s" % (pw,)
+            a_pw = "&pw=%s" % (pw,)
+            for i in hits:
+                i["rp"] += a_pw if "?" in i["rp"] else q_pw
+        else:
+            q_pw = a_pw = ""
+
+        title = self.uparam.get("title") or self.vpath.split("/")[-1]
+        etitle = html_escape(title, True, True)
+
+        baseurl = "%s://%s%s" % (
+            "https" if self.is_https else "http",
+            self.host,
+            self.args.SRS,
+        )
+        feed = "%s%s" % (baseurl, self.req[1:])
+        efeed = html_escape(feed, True, True)
+        edirlink = efeed.split("?")[0] + q_pw
+
+        ret = [
+            """\
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:content="http://purl.org/rss/1.0/modules/content/">
+\t<channel>
+\t\t<atom:link href="%s" rel="self" type="application/rss+xml" />
+\t\t<title>%s</title>
+\t\t<description></description>
+\t\t<link>%s</link>
+\t\t<generator>copyparty-1</generator>
+"""
+            % (efeed, etitle, edirlink)
+        ]
+
+        q = "select fn from cv where rd=? and dn=?"
+        crd, cdn = rem.rsplit("/", 1) if "/" in rem else ("", rem)
+        try:
+            cfn = idx.cur[self.vn.realpath].execute(q, (crd, cdn)).fetchone()[0]
+            bos.stat(os.path.join(vn.canonical(rem), cfn))
+            cv_url = "%s%s?th=jf%s" % (baseurl, vjoin(self.vpath, cfn), a_pw)
+            cv_url = html_escape(cv_url, True, True)
+            zs = """\
+\t\t<image>
+\t\t\t<url>%s</url>
+\t\t\t<title>%s</title>
+\t\t\t<link>%s</link>
+\t\t</image>
+"""
+            ret.append(zs % (cv_url, etitle, edirlink))
+        except:
+            pass
+
+        for i in hits:
+            iurl = html_escape("%s%s" % (baseurl, i["rp"]), True, True)
+            title = unquotep(i["rp"].split("?")[0].split("/")[-1])
+            title = html_escape(title, True, True)
+            tag_t = str(i["tags"].get("title") or "")
+            tag_a = str(i["tags"].get("artist") or "")
+            desc = "%s - %s" % (tag_a, tag_t) if tag_t and tag_a else (tag_t or tag_a)
+            desc = html_escape(desc, True, True) if desc else title
+            mime = html_escape(guess_mime(title))
+            lmod = formatdate(i["ts"])
+            zsa = (iurl, iurl, title, desc, lmod, iurl, mime, i["sz"])
+            zs = (
+                """\
+\t\t<item>
+\t\t\t<guid>%s</guid>
+\t\t\t<link>%s</link>
+\t\t\t<title>%s</title>
+\t\t\t<description>%s</description>
+\t\t\t<pubDate>%s</pubDate>
+\t\t\t<enclosure url="%s" type="%s" length="%d"/>
+"""
+                % zsa
+            )
+            dur = i["tags"].get(".dur")
+            if dur:
+                zs += "\t\t\t<itunes:duration>%d</itunes:duration>\n" % (dur,)
+            ret.append(zs + "\t\t</item>\n")
+
+        ret.append("\t</channel>\n</rss>\n")
+        bret = "".join(ret).encode("utf-8", "replace")
+        self.reply(bret, 200, "text/xml; charset=utf-8")
+        self.log("rss: %d hits, %d bytes" % (len(hits), len(bret)))
+        return True
+
    def handle_propfind(self) -> bool:
        if self.do_log:
            self.log("PFIND %s @%s" % (self.req, self.uname))
--- a/copyparty/u2idx.py
+++ b/copyparty/u2idx.py
@ -95,7 +95,7 @@ class U2idx(object):
        uv: list[Union[str, int]] = [wark[:16], wark]

        try:
-            return self.run_query(uname, vols, uq, uv, False, 99999)[0]
+            return self.run_query(uname, vols, uq, uv, False, True, 99999)[0]
        except:
            raise Pebkac(500, min_ex())

@ -301,7 +301,7 @@ class U2idx(object):
                q += " lower({}) {} ? ) ".format(field, oper)

        try:
-            return self.run_query(uname, vols, q, va, have_mt, lim)
+            return self.run_query(uname, vols, q, va, have_mt, True, lim)
        except Exception as ex:
            raise Pebkac(500, repr(ex))

@ -312,6 +312,7 @@ class U2idx(object):
        uq: str,
        uv: list[Union[str, int]],
        have_mt: bool,
+        sort: bool,
        lim: int,
    ) -> tuple[list[dict[str, Any]], list[str], bool]:
        if self.args.srch_dbg:
@ -458,7 +459,8 @@ class U2idx(object):
        done_flag.append(True)
        self.active_id = ""

-        ret.sort(key=itemgetter("rp"))
+        if sort:
+            ret.sort(key=itemgetter("rp"))

        return ret, list(taglist.keys()), lim < 0 and not clamped

--- a/tests/util.py
+++ b/tests/util.py
@ -122,7 +122,7 @@ class Cfg(Namespace):
    def __init__(self, a=None, v=None, c=None, **ka0):
        ka = {}

-        ex = "chpw daw dav_auth dav_inf dav_mac dav_rt e2d e2ds e2dsa e2t e2ts e2tsr e2v e2vu e2vp early_ban ed emp exp force_js getmod grid gsel hardlink ih ihead magic hardlink_only nid nih no_acode no_athumb no_clone no_dav no_db_ip no_del no_dirsz no_dupe no_lifetime no_logues no_mv no_pipe no_poll no_readme no_robots no_sb_md no_sb_lg no_scandir no_tarcmp no_thumb no_vthumb no_zip nrand nw og og_no_head og_s_title q rand re_dirsz smb srch_dbg stats uqe vague_403 vc ver write_uplog xdev xlink xvol zs"
+        ex = "chpw daw dav_auth dav_inf dav_mac dav_rt e2d e2ds e2dsa e2t e2ts e2tsr e2v e2vu e2vp early_ban ed emp exp force_js getmod grid gsel hardlink ih ihead magic hardlink_only nid nih no_acode no_athumb no_clone no_dav no_db_ip no_del no_dirsz no_dupe no_lifetime no_logues no_mv no_pipe no_poll no_readme no_robots no_sb_md no_sb_lg no_scandir no_tarcmp no_thumb no_vthumb no_zip nrand nw og og_no_head og_s_title q rand re_dirsz rss smb srch_dbg stats uqe vague_403 vc ver write_uplog xdev xlink xvol zs"
        ka.update(**{k: False for k in ex.split()})

        ex = "dedup dotpart dotsrch hook_v no_dhash no_fastboot no_fpool no_htp no_rescan no_sendfile no_ses no_snap no_up_list no_voldump re_dhash plain_ip"