Fixed bug when encountering papers in multiple parts

Author: eoin-cr

README.md

@@ -5,5 +5,14 @@ I have created a python flask webserver so now a website version of the
 code can be run, which should be handier than using the command line.
 
 You can access the scraper at https://examinations.eoin-cr.xyz/ .  It 
-should be fully functional now  (and in my opinion is nicer to use than
-the examinations.ie website)
+should be fully functional now (and in my opinion is nicer to use than
+the examinations.ie website)
+
+---
+
+## Updated in this commit
+
+Previously, there would only be a single url string that was kept track of in
+the url scraper.  However, this would lead to issues when subjects had multiple
+papers in one year for the same level and language.  To rectify this, I've
+loaded the urls into an array instead, and now it works as expected.

script.py

@@ -28,24 +28,35 @@ def scrape(subject, paper_type, exam_type, level, year, language):
                     "MaterialArchive__noTable__sbv__SubjectSelect": subject,
                     "MaterialArchive__noTable__sbh__SubjectSelect": "id"}
     subject_request = requests.post(subject_url, data=subject_data)
+    print(subject_url)
 
     # print(subject_request.text)
     subject_request = subject_request.text.split('\n')
     counter = 0
     for line in subject_request:
         counter += 1
 
+    # the reason for making this array is because sometimes there are multiple
+    # papers for an exam, breaking the old system.  Therefore creating an array
+    # of urls fixes the issue
+    url_arr = ["", "", "", "", ""]
+    arr_count = 0
+
     # Just looking for the lines that match the level and language the user wants
     # and taking that exam paper
     for i in range(counter):
+        # print(counter)
         if language in subject_request[i] and level in subject_request[i]:
-            url += subject_request[i + 2]
-            url = url[8:-31]
+            print(subject_request[i])
+            print(subject_request[i])
+            url_arr[arr_count] = subject_request[i + 2]
+            url_arr[arr_count] = "https://www.examinations.ie/exammaterialarchive/" + url_arr[arr_count][8:-31]
+            arr_count += 1
 
-    if url == "":
-        return "Unable to find exam paper"
-    url = "https://www.examinations.ie/exammaterialarchive/" + url
-    return url
+    if arr_count == 0:
+        url_arr[0] = "Unable to find exam paper"
+        return url_arr
+    return url_arr
 
 
 def val_to_display(value):
@@ -87,9 +98,15 @@ def getvalue():
     # print(subject)
 
     url = scrape(subject, paper_type, exam_type, level, year, language)
+    print(url)
     # sets the default selected options as the value of the last thing submitted, and display the
     # proper name of the input
-    return render_template('index.html', url=url, S_exam=val_to_display(exam_type), S_lang=val_to_display(language),
+
+    # the url1, url2, etc. thing feels like such a bad workaround but it works
+    # so I'm leaving it in for now
+    return render_template('index.html', url1=url[0], url2=url[1], url3=url[2], url4=url[3],
+                           url5=url[4], S_exam=val_to_display(exam_type),
+                           S_lang=val_to_display(language),
                            S_level=val_to_display(level), S_subject=val_to_display(subject),
                            S_type=val_to_display(paper_type), S_year=year,
                            S_exam_V=exam_type, S_lang_V=language, S_level_V=level,

static/style.css

@@ -173,6 +173,17 @@ <h1>Please enter the information about the paper you want</h1>
     </select>
     <input type="submit" value="Submit">
 </form>
-<a href="{{ url }}">{{ url }}</a>
+<!--Ehhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh-->
+<!--There's definitely a much better way of doing this-->
+<a href="{{ url1 }}">{{ url1 }}</a>
+<br>
+<a href="{{ url2 }}">{{ url2 }}</a>
+<br>
+<a href="{{ url3 }}">{{ url3 }}</a>
+<br>
+<a href="{{ url4 }}">{{ url4 }}</a>
+<br>
+<a href="{{ url5 }}">{{ url5 }}</a>
+<br>
 </body>
 </html>