Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Foreign Affairs

Browse Source
This commit is contained in:
Kovid Goyal 2016-02-18 08:56:19 +05:30
parent ce902f5dbd
commit 88519f5a44
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
recipes/foreignaffairs.recipe
View File

@ -3,7 +3,7 @@ import re
def select_form(form): def select_form(form):
return form.attrs.get('class', None) == 'user-login-form' return form.attrs.get('id', None) == 'user-login'
class ForeignAffairsRecipe(BasicNewsRecipe): class ForeignAffairsRecipe(BasicNewsRecipe):
@ -110,9 +110,16 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
return soup return soup
def get_browser(self): def get_browser(self):
import html5lib
from lxml import html
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('https://www.foreignaffairs.com/user?destination=user%3Fop%3Dlo') # mechanize fails to parse the html correctly, so use html5lib to
# sanitize the html first
response = br.open('https://www.foreignaffairs.com/user?destination=user%3Fop%3Dlo')
root = html5lib.parse(response.get_data(), treebuilder='lxml', namespaceHTMLElements=False)
response.set_data(html.tostring(root))
br.set_response(response)
br.select_form(predicate=select_form) br.select_form(predicate=select_form)
br.form['name'] = self.username br.form['name'] = self.username
br.form['pass'] = self.password br.form['pass'] = self.password