def pre_process_story(entry, encoding):
publish_date = entry.get('g_parsed') or entry.get('updated_parsed')
if publish_date:
publish_date = datetime.datetime(*publish_date[:6])
if not publish_date and entry.get('published'):
try:
publish_date = dateutil.parser.parse(
entry.get('published')).replace(tzinfo=None)
except (ValueError, TypeError, OverflowError):
pass
if publish_date:
entry['published'] = publish_date
else:
entry['published'] = datetime.datetime.utcnow() + datetime.timedelta(
seconds=randint(0, 59))
if entry['published'] < datetime.datetime(2000, 1, 1):
entry['published'] = datetime.datetime.utcnow()
# Future dated stories get forced to current date
# if entry['published'] > datetime.datetime.now() + datetime.timedelta(days=1):
if entry['published'] > datetime.datetime.now():
entry['published'] = datetime.datetime.now() + datetime.timedelta(
seconds=randint(0, 59))
# entry_link = entry.get('link') or ''
# protocol_index = entry_link.find("://")
# if protocol_index != -1:
# entry['link'] = (entry_link[:protocol_index+3]
# + urlquote(entry_link[protocol_index+3:]))
# else:
# entry['link'] = urlquote(entry_link)
if isinstance(entry.get('guid'), dict):
entry['guid'] = unicode(entry['guid'])
# Normalize story content/summary
summary = entry.get('summary') or ""
content = ""
if not summary and 'summary_detail' in entry:
summary = entry['summary_detail'].get('value', '')
if entry.get('content'):
content = entry['content'][0].get('value', '')
if len(content) > len(summary):
entry['story_content'] = content.strip()
else:
entry['story_content'] = summary.strip()
if not entry['story_content'] and entry.get('subtitle'):
entry['story_content'] = entry.get('subtitle')
if 'summary_detail' in entry and entry['summary_detail'].get(
'type', None) == 'text/plain':
try:
entry['story_content'] = feedparser._sanitizeHTML(
entry['story_content'], encoding, 'text/plain')
if encoding and not isinstance(entry['story_content'], unicode):
entry['story_content'] = entry['story_content'].decode(
encoding, 'ignore')
except UnicodeEncodeError:
pass
# Add each media enclosure as a Download link
for media_content in chain(
entry.get('media_content', [])[:15],
entry.get('links', [])[:15]):
media_url = media_content.get('url', '')
media_type = media_content.get('type', media_content.get('medium', ''))
if media_url and media_type and entry[
'story_content'] and media_url not in entry['story_content']:
media_type_name = media_type.split('/')[0]
if 'audio' in media_type and media_url:
entry['story_content'] += """<br><br>
<audio controls="controls" preload="none">
<source src="%(media_url)s" type="%(media_type)s" />
</audio>""" % {
'media_url': media_url,
'media_type': media_type
}
elif 'video' in media_type and media_url:
entry['story_content'] += """<br><br>
<video controls="controls" preload="none">
<source src="%(media_url)s" type="%(media_type)s" />
</video>""" % {
'media_url': media_url,
'media_type': media_type
}
elif 'image' in media_type and media_url and media_url not in entry[
'story_content']:
entry[
'story_content'] += """<br><br><img src="%s" />""" % media_url
continue
elif media_content.get(
'rel', '') == 'alternative' or 'text' in media_content.get(
'type', ''):
continue
elif media_type_name in ['application']:
continue
entry['story_content'] += """<br><br>
Download %(media_type)s: <a href="%(media_url)s">%(media_url)s</a>""" % {
'media_type': media_type_name,
'media_url': media_url,
}
entry['guid'] = entry.get('guid') or entry.get('id') or entry.get(
'link') or str(entry.get('published'))
if not entry.get('title'):
entry['title'] = ""
entry['title'] = strip_tags(entry.get('title'))
entry['author'] = strip_tags(entry.get('author'))
entry['story_content'] = attach_media_scripts(entry['story_content'])
return entry
def pre_process_story(entry, encoding):
publish_date = entry.get('published_parsed') or entry.get('updated_parsed')
if publish_date:
publish_date = datetime.datetime(*publish_date[:6])
if not publish_date and entry.get('published'):
try:
publish_date = dateutil.parser.parse(entry.get('published')).replace(tzinfo=None)
except (ValueError, TypeError, OverflowError):
pass
if publish_date:
entry['published'] = publish_date
else:
entry['published'] = datetime.datetime.utcnow()
if entry['published'] < datetime.datetime(2000, 1, 1):
entry['published'] = datetime.datetime.utcnow()
if entry['published'] > datetime.datetime.now() + datetime.timedelta(days=1):
entry['published'] = datetime.datetime.now()
# entry_link = entry.get('link') or ''
# protocol_index = entry_link.find("://")
# if protocol_index != -1:
# entry['link'] = (entry_link[:protocol_index+3]
# + urlquote(entry_link[protocol_index+3:]))
# else:
# entry['link'] = urlquote(entry_link)
if isinstance(entry.get('guid'), dict):
entry['guid'] = unicode(entry['guid'])
# Normalize story content/summary
summary = entry.get('summary') or ""
content = ""
if not summary and 'summary_detail' in entry:
summary = entry['summary_detail'].get('value', '')
if entry.get('content'):
content = entry['content'][0].get('value', '')
if len(content) > len(summary):
entry['story_content'] = content.strip()
else:
entry['story_content'] = summary.strip()
if 'summary_detail' in entry and entry['summary_detail'].get('type', None) == 'text/plain':
try:
entry['story_content'] = feedparser._sanitizeHTML(entry['story_content'], encoding, 'text/plain')
if encoding and not isinstance(entry['story_content'], unicode):
entry['story_content'] = entry['story_content'].decode(encoding, 'ignore')
except UnicodeEncodeError:
pass
# Add each media enclosure as a Download link
for media_content in chain(entry.get('media_content', [])[:5], entry.get('links', [])[:5]):
media_url = media_content.get('url', '')
media_type = media_content.get('type', '')
if media_url and media_type and entry['story_content'] and media_url not in entry['story_content']:
media_type_name = media_type.split('/')[0]
if 'audio' in media_type and media_url:
entry['story_content'] += """<br><br>
<audio controls="controls" preload="none">
<source src="%(media_url)s" type="%(media_type)s" />
</audio>""" % {
'media_url': media_url,
'media_type': media_type
}
elif 'image' in media_type and media_url:
entry['story_content'] += """<br><br><img src="%s" />""" % media_url
continue
elif media_content.get('rel') == 'alternative' or 'text' in media_content.get('type'):
continue
elif media_type_name in ['application']:
continue
entry['story_content'] += """<br><br>
Download %(media_type)s: <a href="%(media_url)s">%(media_url)s</a>""" % {
'media_type': media_type_name,
'media_url': media_url,
}
entry['guid'] = entry.get('guid') or entry.get('id') or entry.get('link') or str(entry.get('published'))
if not entry.get('title') and entry.get('story_content'):
story_title = strip_tags(entry['story_content'])
if len(story_title) > 80:
story_title = story_title[:80] + '...'
entry['title'] = story_title
if not entry.get('title') and entry.get('link'):
entry['title'] = entry['link']
entry['title'] = strip_tags(entry.get('title'))
entry['author'] = strip_tags(entry.get('author'))
entry['story_content'] = attach_media_scripts(entry['story_content'])
return entry
