def parse_result(self, rev):
date = rev['cl_timestamp']
date = date.isoformat() + 'Z'
namespace = NAMESPACE_MAP.get(rev['rc_namespace'])
if namespace and rev['rc_namespace'] > 0:
title = namespace + ':' + rev['rc_title']
else:
title = rev['rc_title']
if namespace is not None:
url = 'https://%s/wiki/%s' % (self.wiki, title.replace(' ', '_'))
else:
# Use curid because we don't know the namespace
url = 'https://%s/w/index.php?curid=%s' % (self.wiki,
rev['rc_cur_id'])
ret = {
'date': date,
'url': url,
'title': title.replace('_', ' '),
'category': self.category
}
ret['created_at'] = date
ret['meta'] = {
'id': url_to_uuid5(ret['url']),
'timestamp': iso8601_to_epoch(date)
}
return ret
def parse_result(self, rev):
date = datetime.datetime.strptime(rev['rc_timestamp'], '%Y%m%d%H%M%S')
date = date.isoformat() + 'Z'
if not rev['rc_new_len']:
rev['rc_new_len'] = 0
if not rev['rc_old_len']:
rev['rc_old_len'] = 0
ret = {
'date':
date,
'url':
'https://%s/w/index.php?diff=%s&oldid=%s' %
(self.wiki, int(rev['rc_this_oldid']), int(rev['rc_last_oldid'])),
'user':
rev['rc_user_text'],
'size':
rev['rc_new_len'] - rev['rc_old_len'],
'comment':
rev['rc_comment'],
'title':
rev['rc_title'].replace('_', ' ')
}
ret['created_at'] = date
ret['meta'] = {
'id': url_to_uuid5(ret['url']),
'timestamp': iso8601_to_epoch(date)
}
return ret
def parse_result(self, rev):
date = datetime.datetime.strptime(rev['rc_timestamp'], '%Y%m%d%H%M%S')
date = date.isoformat() + 'Z'
tags = find_hashtags(rev['rc_comment'])
ret = {
'raw_tags':
tags,
'input_hashtag':
self.tag,
'return_hashtags':
' '.join(tags),
'date':
date,
'url':
'https://%s/w/index.php?diff=%s&oldid=%s' %
(self.wiki, int(rev['rc_this_oldid']), int(rev['rc_last_oldid'])),
'user':
rev['rc_user_text'],
'size':
rev['rc_new_len'] - rev['rc_old_len'],
'comment':
rev['rc_comment'],
'title':
rev['rc_title']
}
ret['created_at'] = date
ret['meta'] = {
'id': url_to_uuid5(ret['url']),
'timestamp': iso8601_to_epoch(date)
}
return ret
def parse_result(self, result):
# Get the timestamp of when the query is runned in the specified format
timestamp = "{:%Y-%m-%dT%H:%M:%SZ}".format(datetime.datetime.now())
meta_id = url_to_uuid5(result['user'])
created_at = result['date']
ts = iso8601_to_epoch(timestamp)
return {'created_at': created_at,
'meta': {'id': meta_id, 'timestamp': ts}}
def parse_result(self, result):
meta_id = url_to_uuid5(result['url'])
created_at = result['date']
ts = iso8601_to_epoch(result['date'])
return {
'created_at': created_at,
'meta': {
'id': meta_id,
'timestamp': ts
}
}
def parse_entry(self, entry):
"""Parse a single feed entry into an IFTTT trigger item."""
# Not sure why, but sometimes we get http entry IDs. If we
# don't have consistency between https/http, we get mutliple
# unique UUIDs for the same entry.
meta_id = url_to_uuid5(entry.id.replace('http:', 'https:'))
date = entry.published_parsed
created_at = utc_to_iso8601(date)
ts = utc_to_epoch(date)
return {'created_at': created_at,
'entry_id': meta_id,
'url': entry.id,
'meta': {'id': meta_id, 'timestamp': ts}}
def parse_entry(self, entry):
"""Parse a single feed entry into an IFTTT trigger item."""
# Not sure why, but sometimes we get http entry IDs. If we
# don't have consistency between https/http, we get mutliple
# unique UUIDs for the same entry.
meta_id = url_to_uuid5(entry.id.replace('http:', 'https:'))
date = entry.published_parsed
created_at = utc_to_iso8601(date)
ts = utc_to_epoch(date)
return {'created_at': created_at,
'entry_id': meta_id,
'url': entry.id,
'meta': {'id': meta_id, 'timestamp': ts}}
def parse_result(self, rev):
date = datetime.datetime.strptime(rev['rc_timestamp'], '%Y%m%d%H%M%S')
date = date.isoformat() + 'Z'
ret = {'date': date,
'url': 'https://%s/w/index.php?diff=%s&oldid=%s' %
(self.wiki,
int(rev['rc_this_oldid']),
int(rev['rc_last_oldid'])),
'user': rev['rc_user_text'],
'size': rev['rc_new_len'] - rev['rc_old_len'],
'comment': rev['rc_comment'],
'title': rev['rc_title']}
ret['created_at'] = date
ret['meta'] = {'id': url_to_uuid5(ret['url']),
'timestamp': iso8601_to_epoch(date)}
return ret
def parse_result(self, rev):
date = rev['cl_timestamp']
date = date.isoformat() + 'Z'
namespace = NAMESPACE_MAP.get(rev['rc_namespace'])
if namespace and rev['rc_namespace'] > 0:
title = namespace + ':' + rev['rc_title']
else:
title = rev['rc_title']
if namespace is not None:
url = 'https://%s/wiki/%s' % (self.wiki, title.replace(' ', '_'))
else:
# Use curid because we don't know the namespace
url = 'https://%s/w/index.php?curid=%s' % (self.wiki, rev['rc_cur_id'])
ret = {'date': date,
'url': url,
'title': title.replace('_', ' '),
'category' : self.category}
ret['created_at'] = date
ret['meta'] = {'id': url_to_uuid5(ret['url']),
'timestamp': iso8601_to_epoch(date)}
return ret
def parse_result(self, page):
url = "https://en.wikipedia.org/wiki/%s?referrer=ifttt-trending"%page['title'].replace(' ', '_')
updated = page['updated'][0:19] + 'Z'
try:
thumbUrl = page['thumbnail']['source']
except KeyError:
thumbUrl = DEFAULT_IMAGE
return {
'thumbURL': thumbUrl,
'bias': page['bias'],
'tags': page['tags'],
'title': page['title'],
'url': url,
'score': page['trendiness'],
'date': updated,
'since': page['start'][0:19] + 'Z',
'edits': page['edits'],
'editors': len(page['contributors']),
'meta': {'id': url_to_uuid5(url),
'timestamp': iso8601_to_epoch(updated)},
}
def parse_result(self, page):
url = "https://en.wikipedia.org/wiki/%s" % page['title'].replace(
' ', '_')
updated = page['updated'][0:19] + 'Z'
try:
thumbUrl = page['thumbnail']['source']
except KeyError:
thumbUrl = 'https://upload.wikimedia.org/wikipedia/commons/6/63/Wikipedia-logo.png'
return {
'thumbURL': thumbUrl,
'bias': page['bias'],
'tags': page['tags'],
'title': page['title'],
'url': url,
'score': page['trendiness'],
'date': updated,
'since': page['start'][0:19] + 'Z',
'edits': page['edits'],
'editors': len(page['contributors']),
'meta': {
'id': url_to_uuid5(url),
'timestamp': iso8601_to_epoch(updated)
},
}
def parse_result(self, page):
url = "https://en.wikipedia.org/wiki/%s?referrer=ifttt-trending" % page[
'title'].replace(' ', '_')
updated = page['updated'][0:19] + 'Z'
try:
thumbUrl = page['thumbnail']['source']
except KeyError:
thumbUrl = DEFAULT_IMAGE
return {
'thumbURL': thumbUrl,
'bias': page['bias'],
'tags': page['tags'],
'title': page['title'],
'url': url,
'score': page['trendiness'],
'date': updated,
'since': page['start'][0:19] + 'Z',
'edits': page['edits'],
'editors': len(page['contributors']),
'meta': {
'id': url_to_uuid5(url),
'timestamp': iso8601_to_epoch(updated)
},
}
def parse_result(self, result):
meta_id = url_to_uuid5(result['url'])
created_at = result['date']
ts = iso8601_to_epoch(result['date'])
return {'created_at': created_at,
'meta': {'id': meta_id, 'timestamp': ts}}
