initial commit. Migration from GitLab

3 files changed, 165 insertions, 0 deletions

diff --git a/webapi/holodex.py b/webapi/holodex.py
new file mode 100644
index 0000000..5f81892
--- /dev/null
+++ b/webapi/holodex.py
@@ -0,0 +1,75 @@
+from webapi.web_api import WebAPI
+from typing import Iterable
+
+
+class HolodexAPI(WebAPI):
+    """
+    Class for interacting with the Holodex API
+    """
+
+    def __init__(self,api_key: str = None,member_count: int = 300,organization: str = "Nijisanji"):
+        super().__init__(api_key=api_key, base_url="https://holodex.net/api/v2/")
+        self.member_count = member_count
+        self.organization = organization
+        self._inactive_channels = []
+        self._channel_data = []
+
+    def get_subscriber_data(self) -> Iterable:
+        """
+        Gets data for all channels in a particular organization
+        """
+        members = self.member_count
+        data = []
+        active_channels = []
+        offset = 0
+        while members > 0:
+            data += self._download_url(
+                f"channels?type=vtuber&offset={offset}&limit=100&org={self.organization}"
+            )
+            members -= 100
+            offset += 100
+        for channel in data:
+            print("DEBUG: ", channel["id"])
+            try:
+                channel["description"] = self.get_channel_description(channel["id"])
+                if channel["inactive"]:
+                    self._inactive_channels.append(channel["id"])
+                    continue
+                active_channels.append(channel)
+            except (KeyError, TypeError, ValueError):
+                print("DEBUG:","An error occured with parsing ", channel["id"], channel["name"])
+                continue
+        self._channel_data = active_channels
+        return active_channels
+
+    def get_view_count(self, channel_id: str) -> int:
+        """
+        Gets the view count for a particular channel
+        """
+        data = self._download_url(f"channels/{channel_id}")
+        return data["view_count"]
+
+    def get_channel_description(self, channel_id: str) -> str:
+        """
+        Gets the description for a particular channel
+        """
+        data = self._download_url(f"channels/{channel_id}")
+        return data["description"]
+    
+    def set_organization(self, organization: str):
+        """
+        Sets the organization for the API
+        """
+        self.organization = organization
+    
+    def get_inactive_channels(self) -> list:
+        """
+        Gets the list of inactive channels
+        """
+        return self._inactive_channels
+
+    def get_generated_channel_data(self) -> list:
+        """
+        Gets the list of channel data
+        """
+        return self._channel_data
diff --git a/webapi/web_api.py b/webapi/web_api.py
new file mode 100644
index 0000000..525994c
--- /dev/null
+++ b/webapi/web_api.py
@@ -0,0 +1,29 @@
+import urllib.request
+import json
+
+
+class WebAPI:
+    """
+    General class for interacting with web APIs
+    """
+
+    def __init__(self, api_key: str, base_url: str) -> None:
+        self.api_key = api_key
+        self.base_url = base_url
+
+    def _download_url(self, query: str, header = 'X-APIKEY') -> dict:
+        """
+        Downloads the URL and returns the result as a string
+        param:
+            query: str - the query to be appended to the base URL
+        """
+        if self.api_key is None:
+            raise Exception("API key not set")
+        opener = urllib.request.build_opener()
+        opener.addheaders = [(header, self.api_key)]
+        urllib.request.install_opener(opener)
+        response = urllib.request.urlopen(self.base_url + query)
+        json_results = response.read()
+        r_obj = json.loads(json_results)
+        response.close()
+        return r_obj
diff --git a/webapi/youtube.py b/webapi/youtube.py
new file mode 100644
index 0000000..a25f5ba
--- /dev/null
+++ b/webapi/youtube.py
@@ -0,0 +1,61 @@
+from webapi.web_api import WebAPI
+
+
+class YouTubeAPI(WebAPI):
+    """
+    Class for interacting with the YouTube API
+    """
+
+    def __init__(self, api_key: str = None):
+        self.api_key = api_key
+        self.base_url = "https://www.googleapis.com/youtube/v3/"
+
+    def _search_matching_id(self, id: str, data: list) -> dict:
+        """
+        Searches for a info matching a given ID
+        param:
+            id: str - the ID to search for
+        """
+        for entry in data:
+            if entry['id'] == id:
+                return entry
+        return None
+
+    def get_data_all_channels(self, channel_tuples: list) -> list:
+        data = []
+        members = len(channel_tuples)
+        request_chunks = [channel_tuples[i:i + 50] for i in range(0, members, 50)]
+        for chunk in request_chunks:
+            channel_ids = [x[0] for x in chunk]
+            channel_names = [x[1] for x in chunk]
+            request_string = ",".join(channel_ids)
+            stats = self._download_url(
+                f"channels?part=statistics&id={request_string}&key={self.api_key}")
+            snippet = self._download_url(
+                f"channels?part=snippet&id={request_string}&key={self.api_key}")
+            stats_list = stats['items']
+            snippet_list = snippet['items']
+            for i in range(len(stats_list)):
+                try:
+                    # group/sub_org is used to further divide channels into subsets (sorta like teams)
+                    # can't think of a better match via YouTube API rn other than customUrl
+                    data_entry = {'english_name': channel_names[i], 'id': channel_ids[i],
+                                  'subscriber_count':
+                                        self._search_matching_id(channel_ids[i], stats_list)['statistics']['subscriberCount'], 
+                                    'view_count':
+                                        self._search_matching_id(channel_ids[i], stats_list)['statistics']['viewCount'],
+                                    'photo': 
+                                        self._search_matching_id(channel_ids[i], snippet_list)['snippet']['thumbnails']['default']['url'],
+                                    'description': 
+                                        self._search_matching_id(channel_ids[i], snippet_list)['snippet']['description'],
+                                    'group': 
+                                        self._search_matching_id(channel_ids[i], snippet_list)['snippet']['customUrl'],
+                                    'video_count':
+                                        self._search_matching_id(channel_ids[i], stats_list)['statistics']['videoCount']
+                                          }
+                    data.append(data_entry)
+                except TypeError:
+                    print("Error NoneType: " + str(channel_ids[i]))
+                except KeyError:
+                    print("Error KeyError: " + str(channel_ids[i]))
+        return data