feat | add the possibility to set a timer between pages

GeovRodri · Dec 16, 2021 · f4b7ba8 · f4b7ba8
1 parent eede875
commit f4b7ba8
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -31,6 +31,8 @@ zap.search(localization="go+goiania++setor-oeste", num_pages=5)
   * default: 'casas'
 * dictionaty\_out (boolean): Specifies the method output (list of objects or dictionary)
   * default: False
+* time_to_wait (float): time to wait until the script scrapes the next page
+  * default: 0
 
 #### Scraped attributes:
 The objects returned from `search` contain the following attributes:

diff --git a/zapimoveis_scraper/__init__.py b/zapimoveis_scraper/__init__.py
@@ -30,6 +30,7 @@
 from urllib.request import Request, urlopen
 from bs4 import BeautifulSoup
 import json
+import time
 
 from zapimoveis_scraper.enums import ZapAcao, ZapTipo
 from zapimoveis_scraper.item import ZapItem
@@ -110,7 +111,7 @@ def get_ZapItem(listing):
     return item
 
 
-def search(localization='go+goiania++setor-marista', num_pages=1, acao=ZapAcao.aluguel.value, tipo=ZapTipo.casas.value, dictionary_out = False):
+def search(localization='go+goiania++setor-marista', num_pages=1, acao=ZapAcao.aluguel.value, tipo=ZapTipo.apartamentos.value, dictionary_out = False, time_to_wait=0):
     page = 1
     items = []
 
@@ -125,7 +126,8 @@ def search(localization='go+goiania++setor-marista', num_pages=1, acao=ZapAcao.a
                 items.append(get_ZapItem(listing))
 
         page += 1
-
+        time.sleep(time_to_wait)
+
     if dictionary_out:
         return convert_dict(items)