Commit 82fc1196 authored by ntome's avatar ntome

[pagesjaunes] take only phone number, ignore fax number

parent 92730c28
......@@ -41,7 +41,10 @@ class ResultsPage(HTMLPage):
obj_name = CleanText('.//a[has-class("denomination-links")]')
obj_address = CleanText('.//a[has-class("adresse")]')
obj_phone = Regexp(CleanText('.//strong[@class="num"]', replace=[(' ', '')]), r'^0(\d{9})$', r'+33\1')
obj_phone = Regexp(
CleanText(
'.//div[has-class("tel-zone")][span[contains(text(),"Tél")]]//strong[@class="num"]',
replace=[(' ', '')]), r'^0(\d{9})$', r'+33\1')
obj_url = AbsoluteLink('.//a[has-class("denomination-links")]')
obj_opening = HasElement('.//span[text()="Horaires"]', NotLoaded, NotAvailable)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment