More stripping \xa0 in adapters.

This commit is contained in:
Jim Miller 2018-08-01 17:46:17 -05:00
parent 49f78457ee
commit 01c836f236
5 changed files with 6 additions and 6 deletions

View file

@ -133,7 +133,7 @@ class FireFlyFansNetSiteAdapter(BaseSiteAdapter):
# which is usualy FireFly on this site, but I'm going to get them
# anyway.a
category = soup.find('span', {'id': 'MainContent_txtItemDetails'})
category = stripHTML(unicode(category).replace(u"\xc2\xa0", ' '))
category = stripHTML(unicode(category).replace(u"\xa0", u' '))
metad = category.split(' ')
for meta in metad:
if ":" in meta:

View file

@ -186,7 +186,7 @@ class FireflyPopulliOrgSiteAdapter(BaseSiteAdapter):
# There alot of nbsp's (non broken spaces) in here, so I'm going to remove them
# I'm also getting rid of the bold tags and the nextline characters to make it
# easier to get the information below
story = repr(story).replace(b'\\xa0', '').replace(' ',' ').replace(
story = repr(story).replace(u'\\xa0', '').replace(' ',' ').replace(
'<b>','').replace('</b>','').replace(r'\n','')
story = self.make_soup(story).find('p')
story_a = story.find('a')
@ -319,7 +319,7 @@ class FireflyPopulliOrgSiteAdapter(BaseSiteAdapter):
# the end of the section, which has alot of extraneous things, then adding my own div
# wrapper, recreating the soup, then getting that div from the soup again, before sending to
# the writers.
story = repr(story).replace(b'\\xa0', '').replace(' ',' ').replace(r'\n','').strip()
story = repr(story).replace(u'\\xa0', '').replace(' ',' ').replace(r'\n','').strip()
story = story[12:]
story = story[:story.find('<p align="center" class="comments">Please <')]
story = '<div class="chaptertext">' + story + '</div>'

View file

@ -286,7 +286,7 @@ class LOTRgficComAdapter(BaseSiteAdapter):
#<br/>
#</p>
## we'll have to remove the non-breaking spaces to get this to work.
metad = unicode(metad).replace(u"\xc2\xa0",'').replace('\n','')
metad = unicode(metad).replace(u"\xa0",'').replace('\n','')
for txt in metad.split('<br/>'):
if 'Challenges:' in txt:
txt = txt.replace('Challenges:','').strip()

View file

@ -191,7 +191,7 @@ class WWWArea52HKHNetAdapter(BaseSiteAdapter):
## I've seen a non-breaking space in some of the storyblocks
## so we are going to remove them.
series = stripHTML(unicode(series.renderContents()).replace(u"\xc2\xa0",'')).strip()
series = stripHTML(unicode(series.renderContents()).replace(u"\xa0",'')).strip()
if len(series) > 0:
self.story.setMetadata('series',series)

View file

@ -147,7 +147,7 @@ class WWWUtopiastoriesComAdapter(BaseSiteAdapter):
for detail in soup.findAll('li'):
det = unicode(detail).replace(u"\xc2\xa0",'')
det = unicode(detail).replace(u"\xa0",'')
heading = stripHTML(det).split(' - ')[0]
text = stripHTML(det).replace(heading+' - ','')
if 'Author' in heading: