projects
/
wikipedia-api-cdsw
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Removed simplejson, updated mwclient, replaced urllib2 with requests
[wikipedia-api-cdsw]
/
wikipedia-raw2.py
diff --git
a/wikipedia-raw2.py
b/wikipedia-raw2.py
index c7eca1be4f72a90bd8a03bdc11b80fa22db2932d..d84b378a770f5606a4318583c501d8306fc2f28c 100644
(file)
--- a/
wikipedia-raw2.py
+++ b/
wikipedia-raw2.py
@@
-1,6
+1,6
@@
import time
import time
-import
simplejson as
json
-from urllib2 import urlopen
+import json
+import requests
url_base = 'https://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=100&rvprop=timestamp|user&format=json'
url_base = 'https://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=100&rvprop=timestamp|user&format=json'
@@
-8,8
+8,8
@@
pages = ["Benjamin_Mako_Hill", "Python", "Data_science"]
for page_title in pages:
for page_title in pages:
- wp_call =
urlopen
(url_base % page_title)
- response = json.loads(wp_call.
read()
)
+ wp_call =
requests.get
(url_base % page_title)
+ response = json.loads(wp_call.
content
)
for page_id in response["query"]["pages"].keys():
page_title = response["query"]["pages"][page_id]["title"]
for page_id in response["query"]["pages"].keys():
page_title = response["query"]["pages"][page_id]["title"]
Benjamin Mako Hill
||
Want to submit a patch?