def _format_tweet(self, job_id, job_title):
self._logging(logging.INFO, 'Formatting tweet.')
# The Twitter API automatically shrinks URLs to 23 characters
url = get_job_url(job_id, job_title, absolute=True)
job_title = job_title.lower()
for hashword in (u'devops', u'développeur', u'développeuse', u'startup', u'cdd', u'cdi', u'stage', u'sysadmin', u'django', u'flask', u'python') :
job_title = job_title.replace(hashword, u'#%s' % hashword)
job_title = job_title.replace(u'adminsys', u'#sysadmin')
job_title = job_title.replace(u'administrateur système', u'#sysadmin')
job_title = job_title.replace(u'administrateur', u'#sysadmin')
job_title = job_title.replace(u'start-up', u'#startup')
job_title = job_title.replace(u'data science', u'#DataScience')
job_title = job_title.replace(u'data scientist', u'#datascientists')
for hashword in (u'nantes', u'lyon', u'paris', u'grenoble', u'toulouse', u'bordeaux', u'marseille', u'lille', u'rennes', u'strasbourg') :
job_title = job_title.replace(hashword, u'#%s' % hashword)
# Tweet format string
tweet_format = u'Recrutement %s %s #emploi'
# The number of punctuation characters in the tweet string format
punctuation = len(tweet_format.replace(u'%s', u''))
total_length = len(job_title) + self.MAX_URL_LENGTH + punctuation
# Make sure our tweet doesn't exceed max_length
if total_length > self.MAX_TWEET_LENGTH:
diff = total_length - self.MAX_TWEET_LENGTH
job_title = job_title[:-diff]
# Return the formatted tweet
return tweet_format % (job_title, url)
def rss(self, limit=50, source=None, *args, **kwargs):
"""
RSS feed of jobs
:param source: source name
:param limit: number of displayed jobs
:return: RSS feed content
"""
site_url = config.get('site.domain_base_url')
feed = feedgenerator.Rss201rev2Feed(
title=u"pyjobs : le job qu'il vous faut en python",
link=site_url,
description=u"Agrégation de jobs python",
language=u"fr",
feed_url=u"http://www.pyjobs.fr/rss?limit=%s" % limit)
jobs = DBSession.query(model.JobAlchemy) \
.order_by(model.JobAlchemy.publication_datetime.desc()) \
.limit(limit)
if source is not None:
jobs = jobs.filter(model.JobAlchemy.source == source)
for job in jobs:
job_slug = slugify(job.title)
feed.add_item(title=job.title,
link=get_job_url(job.id,
job_title=job.title,
absolute=True),
description=job.description,
pubdate=job.publication_datetime,
unique_id="%s/job/%d/%s" %
(site_url, job.id, job_slug))
return feed.writeString('utf-8')
def rss(self, limit=50, source=None, *args, **kwargs):
"""
RSS feed of jobs
:param source: source name
:param limit: number of displayed jobs
:return: RSS feed content
"""
site_url = config.get('site.domain_base_url')
feed = feedgenerator.Rss201rev2Feed(
title=u"pyjobs : le job qu'il vous faut en python",
link=site_url,
description=u"Agrégation de jobs python",
language=u"fr",
feed_url=u"http://www.pyjobs.fr/rss?limit=%s" % limit
)
jobs = DBSession.query(model.JobAlchemy) \
.order_by(model.JobAlchemy.publication_datetime.desc()) \
.limit(limit)
if source is not None:
jobs = jobs.filter(model.JobAlchemy.source == source)
for job in jobs:
job_slug = slugify(job.title)
feed.add_item(
title=job.title,
link=get_job_url(job.id, job_title=job.title, absolute=True),
description=job.description,
pubdate=job.publication_datetime,
unique_id="%s/job/%d/%s" % (site_url, job.id, job_slug)
)
return feed.writeString('utf-8')
def _get_new_jobs(self, jobs):
"""
:param jobs: job to parse
:return: jobs not listed in jobs file
"""
cleaned_jobs = []
with codecs.open(self._jobs_file_path, 'r', 'utf-8') as jobs_file:
jobs_file_read = jobs_file.read()
for job in jobs:
pyjobs_url = get_job_url(job.id, job.title, absolute=True)
if pyjobs_url not in jobs_file_read:
cleaned_jobs.append(job)
return cleaned_jobs
def _get_new_jobs(self, jobs):
"""
:param jobs: job to parse
:return: jobs not listed in jobs file
"""
cleaned_jobs = []
with codecs.open(self._jobs_file_path, 'r', 'utf-8') as jobs_file:
jobs_file_read = jobs_file.read()
for job in jobs:
pyjobs_url = get_job_url(job.id, job.title, absolute=True)
if pyjobs_url not in jobs_file_read:
cleaned_jobs.append(job)
return cleaned_jobs
def _format_tweet(self, job_id, job_title):
self._logging(logging.INFO, 'Formatting tweet.')
# The Twitter API automatically shrinks URLs to 23 characters
url = get_job_url(job_id, job_title, absolute=True)
# Tweet format string
tweet_format = u'%s. %s'
# The number of punctuation characters in the tweet string format
punctuation = len(tweet_format.replace(u'%s', u''))
total_length = len(job_title) + self.MAX_URL_LENGTH + punctuation
# Make sure our tweet doesn't exceed max_length
if total_length > self.MAX_TWEET_LENGTH:
diff = total_length - self.MAX_TWEET_LENGTH
job_title = job_title[:-diff]
# Return the formatted tweet
return tweet_format % (job_title, url)
def _format_tweet(self, job_id, job_title):
self._logging(logging.INFO, 'Formatting tweet.')
# The Twitter API automatically shrinks URLs to 23 characters
url = get_job_url(job_id, job_title, absolute=True)
# Tweet format string
tweet_format = u'%s. %s'
# The number of punctuation characters in the tweet string format
punctuation = len(tweet_format.replace(u'%s', u''))
total_length = len(job_title) + self.MAX_URL_LENGTH + punctuation
# Make sure our tweet doesn't exceed max_length
if total_length > self.MAX_TWEET_LENGTH:
diff = total_length - self.MAX_TWEET_LENGTH
job_title = job_title[:-diff]
# Return the formatted tweet
return tweet_format % (job_title, url)
