Make OpenLP run on Python 3.3-3.5

bzr-revno: 2564
This commit is contained in:
second@tgc.dk 2015-10-28 21:42:51 +00:00 committed by Tim Bentley
commit 6894f92927
2 changed files with 29 additions and 11 deletions

View File

@ -27,7 +27,6 @@ import re
import socket import socket
import urllib.parse import urllib.parse
import urllib.error import urllib.error
from html.parser import HTMLParseError
from bs4 import BeautifulSoup, NavigableString, Tag from bs4 import BeautifulSoup, NavigableString, Tag
@ -290,7 +289,7 @@ class BGExtract(RegistryProperties):
page_source = str(page_source, 'cp1251') page_source = str(page_source, 'cp1251')
try: try:
soup = BeautifulSoup(page_source) soup = BeautifulSoup(page_source)
except HTMLParseError: except Exception:
log.error('BeautifulSoup could not parse the Bible page.') log.error('BeautifulSoup could not parse the Bible page.')
send_error_message('parse') send_error_message('parse')
return None return None
@ -762,7 +761,7 @@ def get_soup_for_bible_ref(reference_url, header=None, pre_parse_regex=None, pre
try: try:
soup = BeautifulSoup(page_source) soup = BeautifulSoup(page_source)
CLEANER_REGEX.sub('', str(soup)) CLEANER_REGEX.sub('', str(soup))
except HTMLParseError: except Exception:
log.exception('BeautifulSoup could not parse the bible page.') log.exception('BeautifulSoup could not parse the bible page.')
if not soup: if not soup:
send_error_message('parse') send_error_message('parse')

View File

@ -23,10 +23,13 @@
The :mod:`~openlp.plugins.songs.lib.songselect` module contains the SongSelect importer itself. The :mod:`~openlp.plugins.songs.lib.songselect` module contains the SongSelect importer itself.
""" """
import logging import logging
import sys
from http.cookiejar import CookieJar from http.cookiejar import CookieJar
from urllib.parse import urlencode from urllib.parse import urlencode
from urllib.request import HTTPCookieProcessor, URLError, build_opener from urllib.request import HTTPCookieProcessor, URLError, build_opener
from html.parser import HTMLParser from html.parser import HTMLParser
if sys.version_info > (3, 4):
from html import unescape
from bs4 import BeautifulSoup, NavigableString from bs4 import BeautifulSoup, NavigableString
@ -129,6 +132,13 @@ class SongSelectImport(object):
if not search_results: if not search_results:
break break
for result in search_results: for result in search_results:
if sys.version_info > (3, 4):
song = {
'title': unescape(result.find('h3').string),
'authors': [unescape(author.string) for author in result.find_all('li')],
'link': BASE_URL + result.find('a')['href']
}
else:
song = { song = {
'title': self.html_parser.unescape(result.find('h3').string), 'title': self.html_parser.unescape(result.find('h3').string),
'authors': [self.html_parser.unescape(author.string) for author in result.find_all('li')], 'authors': [self.html_parser.unescape(author.string) for author in result.find_all('li')],
@ -167,6 +177,9 @@ class SongSelectImport(object):
if callback: if callback:
callback() callback()
song['copyright'] = '/'.join([li.string for li in song_page.find('ul', 'copyright').find_all('li')]) song['copyright'] = '/'.join([li.string for li in song_page.find('ul', 'copyright').find_all('li')])
if sys.version_info > (3, 4):
song['copyright'] = unescape(song['copyright'])
else:
song['copyright'] = self.html_parser.unescape(song['copyright']) song['copyright'] = self.html_parser.unescape(song['copyright'])
song['ccli_number'] = song_page.find('ul', 'info').find('li').string.split(':')[1].strip() song['ccli_number'] = song_page.find('ul', 'info').find('li').string.split(':')[1].strip()
song['verses'] = [] song['verses'] = []
@ -180,8 +193,14 @@ class SongSelectImport(object):
else: else:
verse['lyrics'] += '\n' verse['lyrics'] += '\n'
verse['lyrics'] = verse['lyrics'].strip(' \n\r\t') verse['lyrics'] = verse['lyrics'].strip(' \n\r\t')
if sys.version_info > (3, 4):
song['verses'].append(unescape(verse))
else:
song['verses'].append(self.html_parser.unescape(verse)) song['verses'].append(self.html_parser.unescape(verse))
for counter, author in enumerate(song['authors']): for counter, author in enumerate(song['authors']):
if sys.version_info > (3, 4):
song['authors'][counter] = unescape(author)
else:
song['authors'][counter] = self.html_parser.unescape(author) song['authors'][counter] = self.html_parser.unescape(author)
return song return song