friendica/dir
6
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

suppress some scraping errors when confronted with hybrid/strange

Browse source 
feeds that provide insufficient content-type and choke the html parser.
This commit is contained in:
Friendika 2011-02-02 14:48:27 -08:00
parent fce9988f73
commit ee45dee932
2 changed files with 21 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
boot.php
View file

@ -1366,6 +1366,7 @@ function lrdd($uri) {
else { else {
$html = fetch_url($uri); $html = fetch_url($uri);
$headers = $a->get_curl_headers(); $headers = $a->get_curl_headers();
logger('lrdd: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers); $lines = explode("\n",$headers);
if(count($lines)) { if(count($lines)) {
foreach($lines as $line) { foreach($lines as $line) {
@ -1377,6 +1378,8 @@ function lrdd($uri) {
// don't try and run feeds through the html5 parser // don't try and run feeds through the html5 parser
if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml')))) if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
return array(); return array();
if(stristr($html,'<rss') || stristr($html,'<feed'))
return array();
} }
} }
if(! isset($link)) { if(! isset($link)) {

20
include/Scrape.php
View file

@ -8,12 +8,18 @@ function scrape_dfrn($url) {
$a = get_app(); $a = get_app();
$ret = array(); $ret = array();
logger('scrape_dfrn: url=' . $url);
$s = fetch_url($url); $s = fetch_url($url);
if(! $s) if(! $s)
return $ret; return $ret;
$headers = $a->get_curl_headers(); $headers = $a->get_curl_headers();
logger('scrape_dfrn: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers); $lines = explode("\n",$headers);
if(count($lines)) { if(count($lines)) {
foreach($lines as $line) { foreach($lines as $line) {
@ -93,12 +99,17 @@ function scrape_meta($url) {
$a = get_app(); $a = get_app();
$ret = array(); $ret = array();
logger('scrape_meta: url=' . $url);
$s = fetch_url($url); $s = fetch_url($url);
if(! $s) if(! $s)
return $ret; return $ret;
$headers = $a->get_curl_headers(); $headers = $a->get_curl_headers();
logger('scrape_meta: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers); $lines = explode("\n",$headers);
if(count($lines)) { if(count($lines)) {
foreach($lines as $line) { foreach($lines as $line) {
@ -135,6 +146,9 @@ function scrape_vcard($url) {
$a = get_app(); $a = get_app();
$ret = array(); $ret = array();
logger('scrape_vcard: url=' . $url);
$s = fetch_url($url); $s = fetch_url($url);
if(! $s) if(! $s)
@ -190,15 +204,17 @@ function scrape_feed($url) {
return $ret; return $ret;
$headers = $a->get_curl_headers(); $headers = $a->get_curl_headers();
logger('scrape_feed: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers); $lines = explode("\n",$headers);
if(count($lines)) { if(count($lines)) {
foreach($lines as $line) { foreach($lines as $line) {
if(stristr($line,'content-type:')) { if(stristr($line,'content-type:')) {
if(stristr($line,'application/atom+xml')) { if(stristr($line,'application/atom+xml') || stristr($s,'<feed')) {
$ret['feed_atom'] = $url; $ret['feed_atom'] = $url;
return $ret; return $ret;
} }
if(stristr($line,'application/rss+xml')) { if(stristr($line,'application/rss+xml') || stristr($s,'<rss')) {
$ret['feed_rss'] = $url; $ret['feed_rss'] = $url;
return ret; return ret;
} }