commit 922ee57e65ebb5b920ebcb422118e9e2e62f9eb2
Author: François Pelletier <francois@jevalide.ca>
Date:   Wed Nov 8 15:03:04 2023 -0500

    Initial commit

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..2f13565
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+/messages_a778dec5-8e80-43e0-a1e7-f1019ef4e5e8.csv
+/chatgpt-backup.iml
+/.idea/
diff --git a/extract.py b/extract.py
new file mode 100644
index 0000000..67db800
--- /dev/null
+++ b/extract.py
@@ -0,0 +1,50 @@
+import json
+
+import requests
+import bs4 as bs
+import pandas as pd
+
+# %% URL du lien partagé
+url = ""
+
+# %%
+r = requests.get(url).content
+b = bs.BeautifulSoup(r, "html.parser")
+
+# %%
+j = json.loads(b.findAll("script", {"id": "__NEXT_DATA__"})[0].string)
+
+# %%
+sharedConversationId = j["props"]["pageProps"]['sharedConversationId']
+title = j["props"]["pageProps"]['serverResponse']['data']['title']
+mapping_keys = j["props"]["pageProps"]['serverResponse']['data']['mapping'].keys()
+
+# %%
+messages = []
+for key in mapping_keys:
+    m = j["props"]["pageProps"]['serverResponse']['data']['mapping'][key]
+    try:
+        mapping_id = m["id"]
+        if m["message"]:
+            message_id = m["message"]["id"]
+            message_author_role = m["message"]["author"]["role"]
+            message_create_time = m["message"]["create_time"]
+            message_parts = m["message"]['content']['parts']
+            m_parent = m["parent"]
+            m_children = m["children"]
+            message = {
+                "sharedConversationId": sharedConversationId,
+                "title": title,
+                "id": message_id,
+                "time": message_create_time,
+                "role": message_author_role,
+                "parts": message_parts,
+                "parent": m_parent,
+                "children": m_children
+                       }
+            messages.append(message)
+    except Exception as e:
+        print(e)
+# %%
+messages_df = pd.DataFrame(messages).sort_values(by=['time']).reset_index(drop=True)
+messages_df.to_csv(f"messages_{sharedConversationId}.csv", index=False)
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..5df8a7e
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+requests~=2.31.0
+beautifulsoup4~=4.12.2
+pandas~=2.1.2
\ No newline at end of file