Scrape additional video metadata

1 files changed, 60 insertions, 2 deletions

diff --git a/addon.py b/addon.py
index c173319..ad4b7fb 100644
--- a/addon.py
+++ b/addon.py
@@ -18,6 +18,7 @@ Video plugin for animations posted to Newgrounds.
 """
 
 import concurrent.futures
+import dateutil
 import os
 import sys
 from urllib.parse import urlencode, parse_qsl
@@ -143,9 +144,47 @@ def get_addon_video_info(url):
     """
     html = requests.get(url).text
     soup = BeautifulSoup(html, "html.parser")
+
+    title = soup.find("div", id="embed_header").h2.string
+    thumbnail = soup.find("meta", property="og:image")["content"]
+    sidestats_popularity = soup.find_all('dl', 'sidestats')[0].find_all('dd')
+    views = sidestats_popularity[0].string
+    faves = sidestats_popularity[1].a.string
+    votes = sidestats_popularity[2].string
+    score = sidestats_popularity[3].span.string
+    sidestats_date_and_genre = soup.find_all('dl', 'sidestats')[1].find_all('dd')
+    upload_date = sidestats_date_and_genre[0].string
+    upload_time = sidestats_date_and_genre[1].string
+    genre = sidestats_date_and_genre[2].a.string
+    try:
+        tags = [tag.string for tag in soup.find('dd', 'tags').find_all('a')]
+    except AttributeError as e:
+        tags = []
+    author_comments = ''.join([s for s in soup.find('div', id='author_comments').strings]).strip()
+    authors = [author.string for author in soup.find('ul', 'authorlinks').find_all('a') if author.get("class") is None]
+    if len(soup.find_all('h2', 'rated-a')) != 0:
+        rating = 'a'
+    elif len(soup.find_all('h2', 'rated-m')) != 0:
+        rating = 'm'
+    elif len(soup.find_all('h2', 'rated-t')) != 0:
+        rating = 't'
+    else:
+        rating = 'e'
+
     return {
-        "title": soup.find("div", id="embed_header").h2.string,
-        "thumbnail": soup.find("meta", property="og:image")["content"],
+        "title": title,
+        "thumbnail": thumbnail,
+        "views": views,
+        "faves": faves,
+        "votes": votes,
+        "score": score,
+        "upload_date": upload_date,
+        "upload_time": upload_time,
+        "genre": genre,
+        "tags": tags,
+        "description": author_comments,
+        "authors": authors,
+        "rating": rating,
         "url": url,
     }
 
@@ -211,6 +250,25 @@ def list_videos(genre, category=0, offset=0):
         info_tag = list_item.getVideoInfoTag()
         info_tag.setMediaType("movie")
         info_tag.setTitle(video["title"])
+
+        info_tag.setYear(int(video["upload_date"][-4:]))
+        info_tag.setRating(float(video["score"]), int(video["votes"].replace(',', '')))
+        info_tag.setPlaycount(int(video["views"].replace(',', '')))
+        info_tag.setPlot(video["description"])
+        info_tag.setGenres([video["genre"]])
+        info_tag.setDirectors(video["authors"])
+        info_tag.setPremiered(dateutil.parser.parse(video["upload_date"]).strftime("%Y-%m-%d"))
+        info_tag.setTags(video["tags"])
+
+        if video["rating"] == "a":
+            info_tag.setMpaa("NC-17")
+        elif video["rating"] == "m":
+            info_tag.setMpaa("R")
+        elif video["rating"] == "t":
+            info_tag.setMpaa("PG-13")
+        else:
+            info_tag.setMpaa("PG")
+
         # info_tag.setGenres([genre_info['genre']])
         # info_tag.setPlot(video['plot'])
         # info_tag.setYear(video['year'])