summaryrefslogtreecommitdiff
path: root/load_random.py
diff options
context:
space:
mode:
authorYuval Adam <_@yuv.al>2018-03-15 14:32:56 +0200
committerYuval Adam <_@yuv.al>2018-03-15 14:32:56 +0200
commit06d9e7837dda38c9ee4ee19a5c01796da7a347c0 (patch)
tree18f0ef4e9f7d9ec4874846f19dc0cf56d3686f84 /load_random.py
parent39bc7a979a66a31c12162512c2301c5e43641326 (diff)
Update filesHEADmaster
Diffstat (limited to 'load_random.py')
-rw-r--r--load_random.py25
1 files changed, 25 insertions, 0 deletions
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()