Helper script to run from cron

[webdl] / sbs.py

diff --git a/sbs.py b/sbs.py
index 8014767577cb5029168c49740a4c8cbcbccac974..5304c4ca66d0f1f4d8189ad8d5161c6760d7c7af 100644 (file)
--- a/sbs.py
+++ b/sbs.py
@@ -1,11 +1,10 @@
-#!/usr/bin/env python
-
-from common import grab_html, grab_json, grab_xml, download_hls, Node
+import requests_cache
+from common import grab_html, grab_json, grab_xml, download_hls, Node, append_to_qs
 
 import json
 
 BASE = "http://www.sbs.com.au"
-FULL_VIDEO_LIST = BASE + "/api/video_feed/f/Bgtm9B/sbs-section-programs/?form=json"
+FULL_VIDEO_LIST = BASE + "/api/video_search/v2/?m=1&filters={section}{Programs}"
 VIDEO_URL = BASE + "/ondemand/video/single/%s"
 
 NS = {
@@ -20,11 +19,13 @@ class SbsVideoNode(Node):
         self.can_download = True
 
     def download(self):
-        doc = grab_html(VIDEO_URL % self.video_id, 0)
+        with requests_cache.disabled():
+            doc = grab_html(VIDEO_URL % self.video_id)
         player_params = self.get_player_params(doc)
         release_url = player_params["releaseUrls"]["html"]
 
-        doc = grab_xml(release_url, 0)
+        with requests_cache.disabled():
+            doc = grab_xml(release_url if not release_url.startswith("//") else "http:" + release_url)
         video = doc.xpath("//smil:video", namespaces=NS)[0]
         video_url = video.attrib["src"]
         if not video_url:
@@ -60,14 +61,27 @@ class SbsRootNode(SbsNavNode):
         Node.__init__(self, "SBS", parent)
 
     def fill_children(self):
-        full_video_list = grab_json(FULL_VIDEO_LIST, 3600)
-        category_and_entry_data = self.explode_videos_to_unique_categories(full_video_list)
+        all_video_entries = self.load_all_video_entries()
+        category_and_entry_data = self.explode_videos_to_unique_categories(all_video_entries)
         for category_path, entry_data in category_and_entry_data:
             nav_node = self.create_nav_node(self, category_path)
             nav_node.create_video_node(entry_data)
 
-    def explode_videos_to_unique_categories(self, full_video_list):
-        for entry_data in full_video_list["entries"]:
+    def load_all_video_entries(self):
+        offset = 1
+        amount = 500
+        while True:
+            url = append_to_qs(FULL_VIDEO_LIST, {"range": "%s-%s" % (offset, offset+amount)})
+            data = grab_json(url)
+            entries = data["entries"]
+            if len(entries) == 0:
+                break
+            for entry in entries:
+                yield entry
+            offset += amount
+
+    def explode_videos_to_unique_categories(self, all_video_entries):
+        for entry_data in all_video_entries:
             for category_data in entry_data["media$categories"]:
                 category_path = self.calculate_category_path(
                     category_data["media$scheme"],