From: Antonio Ospite <ao2@ao2.it>
Date: Tue, 9 Jun 2020 22:28:54 +0000 (+0200)
Subject: src/Tweeper.php: only override the User-Agent to a mobile one for twitter.com
X-Git-Tag: v1.4.2~2
X-Git-Url: https://git.ao2.it/tweeper.git/commitdiff_plain/b922824bc561f7f3e31c6f9962d96e9084497ced?hp=50e34cbbe2a9a8d993f0bba6206b01fcc0e1bad3

src/Tweeper.php: only override the User-Agent to a mobile one for twitter.com

Using a mobile User-Agent made it possible to scrape twitter.com again
but it also had side effects: it was forcing facebook.com to serve the
mobile version too.

However tweeper expected the desktop version of facebook.com so this was
breaking support for facebook.com

Scraping the mobile version of facebook.com would be inconvenient
because the xsl would have to be rewritten extensively, and also the
date of posts is not readily available as a timestamp in the mobile
version.

So override the User-Agent for twitter.com only, this makes the code
a little uglier but it works well enough for now.
---

diff --git a/src/Tweeper.php b/src/Tweeper.php
index b794368..f1d579f 100644
--- a/src/Tweeper.php
+++ b/src/Tweeper.php
@@ -36,7 +36,7 @@ date_default_timezone_set('UTC');
  */
 class Tweeper {
 
-  private static $userAgent = "Mozilla/5.0 (Linux; U; Android 4.3; en-us; SM-N900T Build/JSS15J)";
+  private static $userAgent = "Mozilla/5.0";
   private static $maxConnectionTimeout = 5;
   private static $maxConnectionRetries = 5;
 
@@ -455,7 +455,15 @@ class Tweeper {
       return NULL;
     }
 
-    $html = Tweeper::getUrlContents($src_url);
+    // Override User-Agent for twitter.com to force it to serve the mobile UI.
+    if ($host == "twitter.com") {
+      $user_agent = "Mozilla/5.0 (Linux; U; Android 4.3; en-us; SM-N900T Build/JSS15J)";
+    }
+    else {
+      $user_agent = NULL;
+    }
+
+    $html = Tweeper::getUrlContents($src_url, $user_agent);
     if (FALSE === $html) {
       trigger_error("Failed to retrieve $src_url", E_USER_WARNING);
       return NULL;