X-Git-Url: https://code.citadel.org/?a=blobdiff_plain;f=citadel%2Fmodules%2Frssclient%2Fserv_rssclient.c;h=ca05dd62d5067d619f77e030bf797b11a9b450a4;hb=0387f48886a9395d89eaca01cd40ab751610426f;hp=79b1fc3054ba20f1e4f61db19fb0b9aee8611fcb;hpb=887d52d85b8609af10d855819dfa70666d6bbb6c;p=citadel.git diff --git a/citadel/modules/rssclient/serv_rssclient.c b/citadel/modules/rssclient/serv_rssclient.c index 79b1fc305..ca05dd62d 100644 --- a/citadel/modules/rssclient/serv_rssclient.c +++ b/citadel/modules/rssclient/serv_rssclient.c @@ -1,14 +1,16 @@ /* - * Bring external RSS feeds into rooms. + * Bring external RSS and/or Atom feeds into rooms. This module implements a + * very loose parser that scrapes both kinds of feeds and is not picky about + * the standards compliance of the source data. * - * Copyright (c) 2007-2017 by the citadel.org team + * Copyright (c) 2007-2020 by the citadel.org team * - * This program is open source software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 3. + * This program is open source software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 3. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.See the + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ @@ -46,7 +48,6 @@ #include "parsedate.h" #include "database.h" #include "citadel_dirs.h" -#include "md5.h" #include "context.h" #include "internet_addressing.h" @@ -71,7 +72,6 @@ struct rssparser { }; time_t last_run = 0L; -struct CitContext rss_CC; struct rssurl *rsstodo = NULL; @@ -118,12 +118,16 @@ void rss_start_element(void *data, const char *el, const char **attribute) void rss_end_element(void *data, const char *el) { struct rssparser *r = (struct rssparser *)data; + StrBuf *encoded_field; + + if (StrLength(r->CData) > 0) { // strip leading/trailing whitespace from field + StrBufTrim(r->CData); + } if ( // end of a new item(rss) or entry(atom) (!strcasecmp(el, "entry")) || (!strcasecmp(el, "item")) ) { - if (r->msg != NULL) { // Save the message to the rooms // use the link as an item id if nothing else is available @@ -134,7 +138,7 @@ void rss_end_element(void *data, const char *el) // check the use table StrBuf *u = NewStrBuf(); StrBufAppendPrintf(u, "rss/%s", r->item_id); - time_t already_seen = CheckIfAlreadySeen(u, time(NULL), 604800, eUpdate); + int already_seen = CheckIfAlreadySeen(u); FreeStrBuf(&u); if (already_seen == 0) { @@ -176,16 +180,16 @@ void rss_end_element(void *data, const char *el) long msgnum = (-1); for (rr=r->rooms; rr!=NULL; rr=rr->next) { if (rr == r->rooms) { - msgnum = CtdlSubmitMsg(r->msg, NULL, rr->room, 0); + msgnum = CtdlSubmitMsg(r->msg, NULL, rr->room); // in first room, save msg } else { - CtdlSaveMsgPointerInRoom(rr->room, msgnum, 0, NULL); + CtdlSaveMsgPointerInRoom(rr->room, msgnum, 0, NULL); // elsewhere, save a pointer } - syslog(LOG_DEBUG, "Saved message %ld to %s", msgnum, rr->room); + syslog(LOG_DEBUG, "rssclient: saved message %ld to %s", msgnum, rr->room); } } else { - syslog(LOG_DEBUG, "%s was already seen %ld seconds ago", r->item_id, already_seen); + syslog(LOG_DEBUG, "rssclient: already seen %s", r->item_id); } CM_Free(r->msg); @@ -200,15 +204,25 @@ void rss_end_element(void *data, const char *el) else if (!strcasecmp(el, "title")) { // item subject (rss and atom) if ((r->msg != NULL) && (CM_IsEmpty(r->msg, eMsgSubject))) { - CM_SetField(r->msg, eMsgSubject, ChrPtr(r->CData), StrLength(r->CData)); - striplt(r->msg->cm_fields[eMsgSubject]); + encoded_field = NewStrBuf(); + StrBufRFC2047encode(&encoded_field, r->CData); + CM_SetAsFieldSB(r->msg, eMsgSubject, &encoded_field); } } - else if (!strcasecmp(el, "author")) { // author of item (rss and maybe atom) + else if (!strcasecmp(el, "creator")) { // can be used if is not present if ((r->msg != NULL) && (CM_IsEmpty(r->msg, eAuthor))) { - CM_SetField(r->msg, eAuthor, ChrPtr(r->CData), StrLength(r->CData)); - striplt(r->msg->cm_fields[eAuthor]); + encoded_field = NewStrBuf(); + StrBufRFC2047encode(&encoded_field, r->CData); + CM_SetAsFieldSB(r->msg, eAuthor, &encoded_field); + } + } + + else if (!strcasecmp(el, "author")) { // supercedes if both are present + if (r->msg != NULL) { + encoded_field = NewStrBuf(); + StrBufRFC2047encode(&encoded_field, r->CData); + CM_SetAsFieldSB(r->msg, eAuthor, &encoded_field); } } @@ -236,7 +250,6 @@ void rss_end_element(void *data, const char *el) r->link = NULL; } r->link = strdup(ChrPtr(r->CData)); - striplt(r->link); } else if ( @@ -248,7 +261,6 @@ void rss_end_element(void *data, const char *el) r->item_id = NULL; } r->item_id = strdup(ChrPtr(r->CData)); - striplt(r->item_id); } else if ( @@ -261,7 +273,6 @@ void rss_end_element(void *data, const char *el) r->description = NULL; } r->description = strdup(ChrPtr(r->CData)); - striplt(r->description); } if (r->CData != NULL) { @@ -310,13 +321,14 @@ void rssclient_push_todo(char *rssurl, char *roomname) struct rssurl *thisone = NULL; struct rssroom *newroom = NULL; - syslog(LOG_DEBUG, "rssclient_push_todo(%s, %s)", rssurl, roomname); + syslog(LOG_DEBUG, "rssclient: will fetch %s to %s", rssurl, roomname); for (r=rsstodo; r!=NULL; r=r->next) { if (!strcasecmp(r->url, rssurl)) { thisone = r; } } + if (thisone == NULL) { thisone = malloc(sizeof(struct rssurl)); thisone->url = strdup(rssurl); @@ -340,7 +352,7 @@ void rss_pull_one_feed(struct rssurl *url) CURLcode res; StrBuf *Downloaded = NULL; - syslog(LOG_DEBUG, "rss_pull_one_feed(%s)", url->url); + syslog(LOG_DEBUG, "rssclient: fetching %s", url->url); curl = curl_easy_init(); if (!curl) { @@ -350,13 +362,15 @@ void rss_pull_one_feed(struct rssurl *url) Downloaded = NewStrBuf(); curl_easy_setopt(curl, CURLOPT_URL, url->url); + curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L); + curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L); curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L); // Follow redirects curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, CurlFillStrBuf_callback); // What to do with downloaded data curl_easy_setopt(curl, CURLOPT_WRITEDATA, Downloaded); // Give it our StrBuf to work with curl_easy_setopt(curl, CURLOPT_TIMEOUT, 20L); // Time out after 20 seconds res = curl_easy_perform(curl); // Perform the request if (res != CURLE_OK) { - syslog(LOG_WARNING, "Failed to load feed: %s", curl_easy_strerror(res)); + syslog(LOG_WARNING, "rssclient: failed to load feed: %s", curl_easy_strerror(res)); } curl_easy_cleanup(curl); @@ -428,18 +442,17 @@ void rssclient_scan(void) { /* Run no more than once every 15 minutes. */ if ((now - last_run) < 900) { syslog(LOG_DEBUG, - "Client: polling interval not yet reached; last run was %ldm%lds ago", + "rssclient: polling interval not yet reached; last run was %ldm%lds ago", ((now - last_run) / 60), ((now - last_run) % 60) ); return; } - become_session(&rss_CC); - syslog(LOG_DEBUG, "rssclient started"); + syslog(LOG_DEBUG, "rssclient: started"); CtdlForEachRoom(rssclient_scan_room, NULL); rss_pull_feeds(); - syslog(LOG_DEBUG, "rssclient ended"); + syslog(LOG_DEBUG, "rssclient: ended"); last_run = time(NULL); return; } @@ -449,13 +462,9 @@ CTDL_MODULE_INIT(rssclient) { if (!threading) { - syslog(LOG_INFO, "%s", curl_version()); + syslog(LOG_INFO, "rssclient: using %s", curl_version()); CtdlRegisterSessionHook(rssclient_scan, EVT_TIMER, PRIO_AGGR + 300); } - else - { - CtdlFillSystemContext(&rss_CC, "rssclient"); - } return "rssclient"; }