raoul/openlp
1
0
Fork 0
forked from openlp/openlp
Code Issues Pull Requests Projects Releases Wiki Activity

Merge from head.

Browse Source
This commit is contained in:
Raoul Snyman 2010-03-19 23:27:12 +02:00
commit 6c08d4d662
1 changed files with 8 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
openlp/plugins/bibles/lib/http.py
View File

@ -146,14 +146,16 @@ class BGExtract(BibleCommon):
urlstring = u'http://www.biblegateway.com/passage/?search=%s+%s' \ urlstring = u'http://www.biblegateway.com/passage/?search=%s+%s' \
u'&version=%s' % (bookname, chapter, version) u'&version=%s' % (bookname, chapter, version)
log.debug(u'BibleGateway url = %s' % urlstring) log.debug(u'BibleGateway url = %s' % urlstring)
# Let's get the page, and then open it in BeautifulSoup, so as to
# attempt to make "easy" work of bad HTML.
page = urllib2.urlopen(urlstring) page = urllib2.urlopen(urlstring)
soup = BeautifulSoup(page) soup = BeautifulSoup(page)
verses = soup.find(u'div', u'result-text-style-normal') verses = soup.find(u'div', u'result-text-style-normal')
verse_number = 0 verse_number = 0
verse_list = {0: u''} verse_list = {0: u''}
# http://www.codinghorror.com/blog/2009/11/parsing-html-the-cthulhu-way.html
# This is a PERFECT example of opening the Cthulu tag!
# O Bible Gateway, why doth ye such horrific HTML produce?
for verse in verses: for verse in verses:
if isinstance(verse, Tag) and verse.name == u'div' and filter(lambda a: a[0] == u'class', verse.attrs)[0][1] == u'footnotes': if isinstance(verse, Tag) and verse.name == u'div' and filter(lambda a: a[0] == u'class', verse.attrs)[0][1] == u'footnotes':
break break
@ -195,46 +197,10 @@ class BGExtract(BibleCommon):
continue continue
if isinstance(verse, NavigableString): if isinstance(verse, NavigableString):
verse_list[verse_number] = verse_list[verse_number] + verse.replace(u' ', u' ') verse_list[verse_number] = verse_list[verse_number] + verse.replace(u' ', u' ')
# Delete the "0" element, since we don't need it, it's just there for
# some stupid initial whitespace, courtesy of Bible Gateway.
del verse_list[0] del verse_list[0]
# Finally, return the list of verses in a "SearchResults" object.
# xml_string = self._get_web_text(urlstring, self.proxyurl)
# verseSearch = u'<sup class=\"versenum'
# verseFootnote = u'<sup class=\'footnote'
# verse = 1
# i = xml_string.find(u'result-text-style-normal') + 26
# xml_string = xml_string[i:len(xml_string)]
# versePos = xml_string.find(verseSearch)
# bible = {}
# while versePos > -1:
# # clear out string
# verseText = u''
# versePos = xml_string.find(u'</sup>', versePos) + 6
# i = xml_string.find(verseSearch, versePos + 1)
# # Not sure if this is needed now
# if i == -1:
# i = xml_string.find(u'</div', versePos + 1)
# j = xml_string.find(u'<strong', versePos + 1)
# if j > 0 and j < i:
# i = j
# verseText = xml_string[versePos + 7 : i ]
# # store the verse
# bible[verse] = self._clean_text(verseText)
# versePos = -1
# else:
# verseText = xml_string[versePos: i]
# start_tag = verseText.find(verseFootnote)
# while start_tag > -1:
# end_tag = verseText.find(u'</sup>')
# verseText = verseText[:start_tag] + verseText[end_tag + 6:len(verseText)]
# start_tag = verseText.find(verseFootnote)
# # Chop off verse and start again
# xml_string = xml_string[i:]
# #look for the next verse
# versePos = xml_string.find(verseSearch)
# # store the verse
# bible[verse] = self._clean_text(verseText)
# verse += 1
return SearchResults(bookname, chapter, verse_list) return SearchResults(bookname, chapter, verse_list)
class CWExtract(BibleCommon): class CWExtract(BibleCommon):