From 06d9e7837dda38c9ee4ee19a5c01796da7a347c0 Mon Sep 17 00:00:00 2001 From: Yuval Adam <_@yuv.al> Date: Thu, 15 Mar 2018 14:32:56 +0200 Subject: Update files --- load_random.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 load_random.py (limited to 'load_random.py') diff --git a/load_random.py b/load_random.py new file mode 100644 index 0000000..0f86230 --- /dev/null +++ b/load_random.py @@ -0,0 +1,25 @@ +import wikipedia + +from redisearch import Client, TextField + + +class RandomWikipediaImport(object): + + def __init__(self): + self.rs = Client('wikipedia') + self.rs.create_index((TextField('title', weight=5.0), TextField('body'))) + print(f'>>> Created index') + + def insert_random_loop(self): + i = 1 + while True: + ra = wikipedia.random() + article = wikipedia.page(ra) + self.rs.add_document(f'doc{i}', title=article.title, body=article.content) + print(f'>>> Inserted {article.title}') + i += 1 + + +if __name__ == '__main__': + rwi = RandomWikipediaImport() + rwi.insert_random_loop() -- cgit v1.3.1