Merge pull request #185 from g0v/improve-regex-for-js

bug: remove comman inside string in NUXT hydration
g0v · Oct 29, 2024 · 5e4f547 · 5e4f547
2 parents 65c9ecb + 173bc3b
commit 5e4f547
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/scrapy-tw-rental-house/scrapy_twrh/spiders/rental591/util.py b/scrapy-tw-rental-house/scrapy_twrh/spiders/rental591/util.py
@@ -148,6 +148,9 @@ def list_values(self):
 
         # dirty hack 1, remove comma from "12,345" XD
         value_str = re.sub(r'"(\d+),(\d+)"', r'\1\2', value_str)
+        # dirty hack 2, we won't need "市中心,拎包入住,含車位" for now.
+        # we have to remove the comma in the string
+        value_str = re.sub(r'"(([^\u0000-\u007F]|\\)[^",]*),[^"]+"', r'\1', value_str)
         ret = []
         for raw_value in value_str.split(','):
             # remove leading and trailing double quotes