nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

use regexp groups with pages

Browse source
This commit is contained in:
Christophe Benz 2010-07-12 03:14:26 +02:00
commit b460b81ba8
1 changed files with 8 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

10
weboob/tools/browser/browser.py
View file

@ -91,10 +91,12 @@ class BasePage(object):
""" """
Base page Base page
""" """
def __init__(self, browser, document, url=''): def __init__(self, browser, document, url='', groups=None, group_dict=None):
self.browser = browser self.browser = browser
self.document = document self.document = document
self.url = url self.url = url
self.groups = groups
self.group_dict = group_dict
def on_loaded(self): def on_loaded(self):
""" """
@ -304,11 +306,15 @@ class BaseBrowser(mechanize.Browser):
# Find page from url # Find page from url
pageCls = None pageCls = None
page_groups = None
page_group_dict = None
for key, value in self.PAGES.items(): for key, value in self.PAGES.items():
regexp = re.compile('^%s$' % key) regexp = re.compile('^%s$' % key)
m = regexp.match(result.geturl()) m = regexp.match(result.geturl())
if m: if m:
pageCls = value pageCls = value
page_groups = m.groups()
page_group_dict = m.groupdict()
break break
# Not found # Not found
@ -325,7 +331,7 @@ class BaseBrowser(mechanize.Browser):
self.last_update = time.time() self.last_update = time.time()
document = self.parser.parse(result, self.ENCODING) document = self.parser.parse(result, self.ENCODING)
self.page = pageCls(self, document, result.geturl()) self.page = pageCls(self, document, result.geturl(), groups=page_groups, group_dict=page_group_dict)
self.page.on_loaded() self.page.on_loaded()
if self.password is not None and not self.is_logged(): if self.password is not None and not self.is_logged():