From 13b54779952bd1f56bac6d5fd8490b0bfa12f71d Mon Sep 17 00:00:00 2001
From: neodarz <neodarz@neodarz.net>
Date: Mon, 5 Aug 2019 09:45:26 +0200
Subject: Add ability to download a collection

---
 artetv_dl/__main__.py | 57 +++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 44 insertions(+), 13 deletions(-)

(limited to 'artetv_dl')

diff --git a/artetv_dl/__main__.py b/artetv_dl/__main__.py
index 8e6c759..58ce3d9 100755
--- a/artetv_dl/__main__.py
+++ b/artetv_dl/__main__.py
@@ -6,20 +6,8 @@ from bs4 import BeautifulSoup
 from urllib.request import urlopen, unquote, urlretrieve
 import re, json, sys
 
-def main():
-    if len(sys.argv) != 2:
-        print("Usage:")
-        print("    "+sys.argv[0]+" <arte.tv_link>")
-        print("Example:")
-        print("    "+sys.argv[0]+" https://www.arte.tv/fr/videos/051868-000-A/liberte-egalite-indemnites-vers-un-revenu-universel/")
-        sys.exit(0)
-
-    url = sys.argv[1]
-
-    programId = re.findall('[0-9A-Z]{6}-[0-9A-Z]{3}-[0-9A-Z]', url)[0]
-
-    url = "https://api.arte.tv/api/player/v1/config/en/{}".format(programId)
 
+def download(url):
     content = urlopen(url)
     json_data = json.loads(content.read().decode())
     name = json_data['videoJsonPlayer']['VTI']
@@ -34,5 +22,48 @@ def main():
         print(e)
 
 
+def main():
+    if len(sys.argv) != 2:
+        print("Usage:")
+        print("    "+sys.argv[0]+" <arte.tv_link>")
+        print("Example:")
+        print("    "+sys.argv[0]+" https://www.arte.tv/fr/videos/051868-000-A/liberte-egalite-indemnites-vers-un-revenu-universel/")
+        sys.exit(0)
+
+    url = sys.argv[1]
+
+    programId = re.findall('[0-9A-Z]{6}-[0-9A-Z]{3}-[0-9A-Z]', url)
+
+    collection = re.findall('[0-9A-Z]{2}-[0-9A-Z]{6}', url)
+
+    if len(programId) > 0:
+        url = "https://api.arte.tv/api/player/v1/config/en/{}".format(programId[0])
+
+        download(url)
+    elif len(collection) > 0:
+        content = urlopen(url)
+
+        soup = BeautifulSoup(content, "lxml")
+
+        links = soup.find_all("a", {"class": "next-teaser__link"}, href=True)
+
+        for link in links:
+            programId = re.findall('[0-9A-Z]{6}-[0-9A-Z]{3}-[0-9A-Z]', link['href'])
+            url = "https://api.arte.tv/api/player/v1/config/en/{}".format(programId[0])
+            download(url)
+
+        if not links:
+            url = "https://api.arte.tv/api/player/v1/collectionData/en/{}".format(collection[0])
+            content = urlopen(url)
+            json_data = json.loads(content.read().decode())
+            videos = json_data['videos']
+            for video in videos:
+                url = "https://api.arte.tv/api/player/v1/config/en/{}".format(video['programId'])
+                download(url)
+
+    else:
+        print("This is not a valid url")
+
+
 if __name__ == "__main__":
     main()
-- 
cgit v1.2.1