Writes out a course in the required folder structure

.gitignore

@@ -1,5 +1,6 @@
 # Outputs
 *.md
+*.png
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

README.md

@@ -30,7 +30,7 @@ and the format to convert the material to.
 
 ## Remaining development
 
-- Only return blocks and lectures which are published, and the latest version (normally only the latest version is published, but not necessarily).
+- [ ] Only return blocks and lectures which are published, and the latest version (normally only the latest version is published, but not necessarily).
   Currently the relations store all blocks, including earlier versions of the same block, that are included in a lecture.
   The same for lectures and courses.
-- We need to re-do the embedding of images in the markdown documents. Images are stored in the media library, but are then uploaded to an amazon server, so these can be downloaded from the urls embedded in the document and then redirected to a local location.
+- [ ] We need to re-do the embedding of images in the markdown documents. Images are stored in the media library, but are then uploaded to an amazon server, so these can be downloaded from the urls embedded in the document and then redirected to a local location.

get_block.py

@@ -5,19 +5,20 @@
 >>> python get_block.py
 
 """
+from matplotlib.widgets import Slider, SliderBase
 import requests
 from typing import Dict, Union, Any
 from json import loads, dumps
 
 def get_lecture_block(id: str):
     """Retrieves the contents of a lecture block from the teaching kit website
-
     Arguments
     ---------
         id (str): The id of the lecture block to retrieve
     """
-    url = f"https://teachingkit.climatecompatiblegrowth.com/api/blocks/{id}?locale=en&populate=*"
-    response = requests.get(url)
+    url = f"https://teachingkit.climatecompatiblegrowth.com/api/blocks/{id}"
+    payload = {'locale': 'en', 'populate': '*'}
+    response = requests.get(url, params=payload)
 
     return response.json()
 
@@ -32,11 +33,16 @@ def print_keys(dict: Union[Dict, Any]):
 
 
 if __name__ == "__main__":
-    block = get_lecture_block(4)
+    block = get_lecture_block(5)
     attributes = block['data']['attributes']
 
     print(f"Attributes: {attributes.keys()}")
 
+    print(f"Version number: {attributes['versionNumber']}")
+    print(f"Version: {[x['id'] for x in attributes['versions']['data']]}")
+
+    print(f"Published at: {attributes['publishedAt']}")
+
     lectures = [x['attributes'] for x in attributes['Lectures']['data']]
     for lecture in lectures:
         print(f"This block is part of lecture '{lecture['Title']}'")

get_course.py

@@ -20,8 +20,9 @@ def get_course(id: str):
     ---------
         id (str): The id of the course to retrieve
     """
-    url = f"https://teachingkit.climatecompatiblegrowth.com/api/courses/{id}?locale=en&populate=*"
-    response = requests.get(url)
+    url = f"https://teachingkit.climatecompatiblegrowth.com/api/courses/{id}"
+    payload = {'locale': 'en', 'populate': '*'}
+    response = requests.get(url, params=payload)
 
     return response.json()
 
@@ -43,6 +44,7 @@ def print_keys(dict: Union[Dict, Any]):
 
     title = attributes['Title']
     print(f"Course title: {title}")
+
 
     outcomes = [x['LearningOutcome'] for x in attributes['LearningOutcomes']]
     print(f"Outcomes: {outcomes}")
@@ -52,17 +54,3 @@ def print_keys(dict: Union[Dict, Any]):
         print(f"This course contains lecture: '{lecture['id']}: {lecture['attributes']['Title']}'")
 
 
-    # authors = [x['attributes'] for x in attributes['LectureCreators']['data']]
-
-    # print("This lecture lecture was written by:")
-    # for author in authors:
-    #     print(f"{author['FirstName']} {author['LastName']} {author['Email']} {author['ORCID']}")
-
-
-
-    # lecture_id = lecture['data']['id']
-    # document = attributes['Abstract']
-    # with open(f"lecture_{lecture_id}.md", 'wt') as markdown_file:
-    #     markdown_file.write(f"# {title}\n\n")
-    #     markdown_file.write(document)
-

get_keywrd.py

@@ -0,0 +1,50 @@
+import nltk
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.probability import FreqDist
+import markdown
+
+from get_lecture import get_lecture
+
+# Download NLTK data if not already downloaded
+nltk.download('punkt')
+nltk.download('stopwords')
+
+# Function to extract keywords from a text
+def extract_keywords(text):
+    # Tokenize the text
+    words = word_tokenize(text.lower())
+
+    # Remove stopwords and punctuation
+    stopwords_set = set(stopwords.words('english'))
+    words = [word for word in words if word.isalnum() and word not in stopwords_set]
+
+    # Calculate word frequency
+    word_freq = FreqDist(words)
+
+    # Select the top 10 most frequent words as keywords
+    keywords = [word for word, _ in word_freq.most_common(10)]
+
+    return keywords
+
+ #Extract keywords from the lecture note
+keywords = extract_keywords('get_lecture')
+
+# Generate Markdown content with keywords
+#markdown_content = "\n".join([f"- {keyword}" for keyword in keywords])
+
+# Save the Markdown content to a file
+#with open("keywords.md", "w") as file:
+    #file.write(markdown_content)
+
+#print("Keywords extracted and saved to 'keywords.md'")
+
+# Optional: Print the extracted keywords
+#print("Extracted Keywords:")
+for keyword in keywords:
+    print(keyword)
+
+
+
+
+

get_lecture.py

@@ -4,9 +4,9 @@
 
 >>> python get_lecture.py
 
-
 """
 import requests
+#import keywords
 from typing import Dict, Union, Any
 
 
@@ -17,8 +17,9 @@ def get_lecture(id: str):
     ---------
         id (str): The id of the lecture block to retrieve
     """
-    url = f"https://teachingkit.climatecompatiblegrowth.com/api/lectures/{id}?locale=en&populate=*"
-    response = requests.get(url)
+    url = f"https://teachingkit.climatecompatiblegrowth.com/api/lectures/{id}"
+    payload = {'locale': 'en', 'populate': '*'}
+    response = requests.get(url, params=payload)
 
     return response.json()
 
@@ -39,10 +40,13 @@ def print_keys(dict: Union[Dict, Any]):
 
     print(f"Attributes: {attributes.keys()}")
 
+    print(f"Version number: {attributes['versionNumber']}")
+    print(f"Version: {attributes['versions']}")
+
     blocks = attributes['Blocks']['data']
-    print(blocks)
+    # print(blocks)
     for block in blocks:
-        print(f"This lecture contains block {block['id']}: '{block['attributes']['Title']}'")
+        print(f"This lecture contains block {block['id']}: '{block['attributes']['Title']}'") #'{block['attributes']['keywords']}")
 
     authors = [x['attributes'] for x in attributes['LectureCreators']['data']]
 
@@ -56,10 +60,12 @@ def print_keys(dict: Union[Dict, Any]):
 
     title = attributes['Title']
     print(title)
+    keywords = attributes['keywords']
+    print(keywords)
 
     lecture_id = lecture['data']['id']
     document = attributes['Abstract']
-    with open(f"lecture_{lecture_id}.md", 'wt') as markdown_file:
-        markdown_file.write(f"# {title}\n\n")
-        markdown_file.write(document)
+    # with open(f"lecture_{lecture_id}.md", 'wt') as markdown_file:
+    #     markdown_file.write(f"# {title}\n\n")
+    #     markdown_file.write(document)
 

test_write_out_course.py

@@ -0,0 +1,8 @@
+from write_out_course import extract_urls
+
+def test_extract_urls():
+
+    test_string = "![Fig_1.4.2b.png](https://test.com/1.png)![Fig_1.4.2c.png](https://test.com/2.png)"
+    urls = extract_urls(test_string)
+    print(urls)
+    assert len(urls) == 2