Script pour savoir qui a dit de vilain gros mots

million/analyze/wordFinder.py

@@ -0,0 +1,13 @@
+import re
+from typing import List
+from million.model.message import Message
+
+
+def _wordFilter(msg: Message, regexs: List[str]) -> bool:
+    return msg.content and any(
+        re.search(rgx, msg.content) for rgx in regexs
+        )
+
+def findWords(messages: List[Message], words: List[Message]) -> List[Message]:
+    rWords = [r"\b"+word+r"\b" for word in words]
+    return filter(lambda m: _wordFilter(m, rWords), messages)

scripts/find_gromots.py

@@ -0,0 +1,17 @@
+
+from million.analyze.wordFinder import findWords
+from million.parse.fb_exports import FacebookExportParser
+
+
+DATA_PATH = './data/'
+
+parser = FacebookExportParser()
+
+export = parser.parse(DATA_PATH)
+
+grosMots = ['merde', 'putain', 'bite', 'nichon', 'con(ne)?', 'baiser?']
+
+msgGromots = findWords(export.messages, grosMots)
+
+for gromot in msgGromots:
+    print(f"{gromot.sender_name} : {gromot.content}")