summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/wayback_static.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2021-11-03 13:57:18 -0700
committerBryan Newbold <bnewbold@robocracy.org>2021-11-03 16:46:07 -0700
commit5d29d1336afc90d3575a0379a9e9d9bdac8d1856 (patch)
treec22755cdf2615453ab1f3b7ddaf13becd946a63d /python/fatcat_tools/importers/wayback_static.py
parentcaf1cb316ed18820f3239a285ef14bf45ef963a2 (diff)
downloadfatcat-5d29d1336afc90d3575a0379a9e9d9bdac8d1856.tar.gz
fatcat-5d29d1336afc90d3575a0379a9e9d9bdac8d1856.zip
typing: relatively simple type check fixes
These mostly add new variable names so that existing variables aren't overwritten with a new type; delay coercing '{}' or '[]' to 'None' until the last minute; adding is-not-None checks to conditional clauses; and similar small changes.
Diffstat (limited to 'python/fatcat_tools/importers/wayback_static.py')
-rwxr-xr-xpython/fatcat_tools/importers/wayback_static.py23
1 files changed, 12 insertions, 11 deletions
diff --git a/python/fatcat_tools/importers/wayback_static.py b/python/fatcat_tools/importers/wayback_static.py
index f9ee29c9..3c619b14 100755
--- a/python/fatcat_tools/importers/wayback_static.py
+++ b/python/fatcat_tools/importers/wayback_static.py
@@ -89,22 +89,23 @@ def lookup_cdx(
) -> Optional[WebcaptureCdxLine]:
sys.stderr.write(embed_url + "\n")
assert embed_url.startswith("/web/")
- embed_url = embed_url.split("/")
- timestamp = embed_url[2]
+ embed_url_segments = embed_url.split("/")
+ timestamp = embed_url_segments[2]
if timestamp.endswith("_"):
timestamp = timestamp[:-3]
- url = "/".join(embed_url[3:])
+ url = "/".join(embed_url_segments[3:])
# print((timestamp, url))
+ params: Dict = dict(
+ url=url,
+ closest=timestamp,
+ sort="closest",
+ resolveRevisits="true",
+ matchType="exact",
+ limit=1,
+ )
resp = REQ_SESSION.get(
CDX_API_BASE,
- params=dict(
- url=url,
- closest=timestamp,
- sort="closest",
- resolveRevisits="true",
- matchType="exact",
- limit=1,
- ),
+ params=params,
)
resp.raise_for_status()
# print(resp.url)