def handle_noargs(self, **options):
doc_type = "RCR SRP"
file_type = "html"
base_url = 'http://repcloakroom.house.gov/news/'
page = urllib2.urlopen(
"http://repcloakroom.house.gov/news/DocumentQuery.aspx?DocumentTypeID=1501&Page=1"
)
add_date = datetime.datetime.now()
soup = BeautifulSoup(page)
rows = soup.findAll('span', {"class": "middlecopy"})
for row in rows:
if row.find('span', {"class": "middleheadline"}):
title = str(
row.find('span', {
"class": "middleheadline"
}).contents[1]).replace('<b>', '').replace('</b>',
'').strip()
bill_list = extract_legislation(title)
date_str = row.find('span', {
"class": "middleheadline"
}).parent.contents[5].contents[0].replace(' -',
'').strip()
release_date = time.strftime(
'%Y-%m-%d', time.strptime(date_str, '%b %d, %Y'))
year = int(
time.strftime('%Y', time.strptime(date_str, '%b %d, %Y')))
congress = congress_from_year(year)
description = unicode(
row.find('span', {
"class": "middleheadline"
}).parent.contents[6]).strip()
if not bill_list:
bill_list = extract_legislation(description)
if title == "":
title = "".join(bill_list)
file_name = row.find('span', {
"class": "middleheadline"
}).parent.contents[7]['href']
original_url = "%s%s" % (base_url, file_name)
gov_id = "SRP-%s-%s-%s" % (congress, bill_list[0].replace(
' ', '').replace('.', ''), release_date)
doc = {
'gov_id': gov_id,
'original_url': original_url,
'file_name': file_name,
'title': title,
'description': description,
'congress': congress,
'year': year,
'release_date': release_date,
'bill_list': bill_list
}
print doc
def handle_noargs(self, **options):
doc_type = "CBO CE"
file_type = "pdf"
d = feedparser.parse("http://www.cbo.gov/rss/latest10.xml")
for entry in d.entries:
title_dict = split_title(entry.title)
release_date = entry.updated_parsed
release_date = datetime.datetime(release_date[0], release_date[1],
release_date[2])
congress = congress_from_year(release_date.year)
add_date = datetime.datetime.now()
title = title_dict['title']
bill_list = extract_legislation(title)
if len(bill_list) > 0:
bill_num = bill_list[0]
gov_id = "%s-%s" % (congress, bill_num.replace(
'.', '').replace(' ', ''))
else:
bill_num = None
gov_id = None
if 'description' in entry:
description = entry.description
original_url = entry.link
entry = {
'release_date': release_date,
'congress': congress,
'add_date': add_date,
'title': title,
'description': description,
'bill_list': bill_list,
'original_url': original_url
}
print entry
def handle_noargs(self, **options):
doc_type = "DPC LB"
file_type = "html"
add_date = datetime.datetime.now()
year = add_date.year
congress = congress_from_year(year)
url_prefix = "http://dpc.senate.gov/"
url = "%sdpcreports.cfm?cf_year=%s&doctype=lb" % (url_prefix, year)
page = urllib2.urlopen(url)
soup = BeautifulSoup(page)
rows = soup.findAll('p', {"class": "doclist"})
for row in rows:
file_name = row('a')[0]['href'].strip()
p = re.compile('dpcdoc\.cfm\?doc_name=')
standard_format = p.findall(file_name)
if standard_format:
gov_id = file_name.replace('dpcdoc.cfm?doc_name=', '').upper()
else:
gov_id = None
original_url = "%s%s" % (url_prefix, file_name)
local_file = ''
title = row('a')[0].string
description = ''
bill_list = extract_legislation(title)
date_str = row.contents[3].string.replace('(', '').replace(')', '')
release_date = time.strftime('%Y-%m-%d',
time.strptime(date_str, '%m/%d/%y'))
matches = Document.objects.filter(doc_type=doc_type,
gov_id=gov_id,
release_date=release_date)
if len(matches) == 0:
if gov_id:
local_file = archive_file(original_url, gov_id, doc_type,
file_type)
time.sleep(2)
full_text = None
doc = Document(gov_id=gov_id,
release_date=release_date,
add_date=add_date,
title=title,
description=description,
doc_type=doc_type,
original_url=original_url,
local_file=local_file,
full_text=full_text)
doc.save()
for bill_num in bill_list:
bill_dupe = DocumentLegislation.objects.filter(
congress=congress).filter(
bill_num=bill_num).filter(document=doc)
if not bill_dupe:
bill = DocumentLegislation(congress=congress,
bill_num=bill_num,
document=doc)
bill.save()
def handle_noargs(self, **options):
doc_type = "RCR SRP"
file_type = "html"
base_url = 'http://repcloakroom.house.gov/news/'
page = urllib2.urlopen("http://repcloakroom.house.gov/news/DocumentQuery.aspx?DocumentTypeID=1501&Page=1")
add_date = datetime.datetime.now()
soup = BeautifulSoup(page)
rows = soup.findAll('span', { "class":"middlecopy" })
for row in rows:
if row.find('span', { "class":"middleheadline" }):
title = str(row.find('span', { "class":"middleheadline" }).contents[1]).replace('<b>', '').replace('</b>', '').strip()
bill_list = extract_legislation(title)
date_str = row.find('span', { "class":"middleheadline" }).parent.contents[5].contents[0].replace(' -', '').strip()
release_date = time.strftime('%Y-%m-%d', time.strptime(date_str, '%b %d, %Y'))
year = int(time.strftime('%Y', time.strptime(date_str, '%b %d, %Y')))
congress = congress_from_year(year)
description = unicode(row.find('span', { "class":"middleheadline" }).parent.contents[6]).strip()
if not bill_list:
bill_list = extract_legislation(description)
if title == "":
title = "".join(bill_list)
file_name = row.find('span', { "class":"middleheadline" }).parent.contents[7]['href']
original_url = "%s%s" % (base_url, file_name)
gov_id = "SRP-%s-%s-%s" % (congress, bill_list[0].replace(' ', '').replace('.', ''), release_date)
matches = Document.objects.filter(doc_type=doc_type, gov_id=gov_id, release_date=release_date)
if len(matches) == 0:
print_url = original_url.replace('DocumentSingle', 'DocumentPrint')
#print_page = urllib2.urlopen(print_url).read()
#full_text = ''.join(BeautifulSoup(print_page).findAll(text=True)).replace('DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"', '').strip()
#full_text = re.sub("\s+" , " ", full_text)
full_text = None
if gov_id:
local_file = archive_file(print_url, gov_id, doc_type, file_type)
doc = Document(gov_id=gov_id, release_date=release_date, add_date=add_date, title=title, description=description, doc_type=doc_type, original_url=original_url, local_file=local_file, full_text=full_text)
doc.save()
for bill in bill_list:
bill_num = clean_bill_num(bill)
bill = DocumentLegislation(congress=congress, bill_num=bill_num, document=doc)
bill.save()
def handle_noargs(self, **options):
docs = Document.objects.all()
for doc in docs:
bill_list = extract_legislation(doc.title)
congress = congress_from_year(doc.release_date.year)
if bill_list:
i = 0
for bill_num in bill_list:
bill_dupe = DocumentLegislation.objects.filter(
congress=congress).filter(bill_num=bill_num).filter(
document=doc)
if not bill_dupe:
bill = DocumentLegislation(congress=congress,
bill_num=bill_num,
document=doc)
bill.save()
print "%s %s" % (doc.gov_id, bill_list)
def handle_noargs(self, **options):
doc_type = "CBO CE"
file_type = "pdf"
d = feedparser.parse("http://www.cbo.gov/rss/latest10.xml")
for entry in d.entries:
title_dict = split_title(entry.title)
release_date = entry.updated_parsed
release_date=datetime.datetime(release_date[0], release_date[1], release_date[2])
congress = congress_from_year(release_date.year)
add_date = datetime.datetime.now()
title = title_dict['title']
bill_list = extract_legislation(title)
if len(bill_list) > 0:
bill_num = bill_list[0]
gov_id = "%s-%s" % (congress, bill_num.replace('.', '').replace(' ', ''))
else:
bill_num = None
gov_id = None
if 'description' in entry:
description = entry.description
original_url = entry.link
matches = Document.objects.filter(doc_type=doc_type, gov_id=gov_id, release_date=release_date)
if len(matches) == 0:
if gov_id:
local_file = archive_file(original_url, gov_id, doc_type, file_type)
#full_text = pdf_extract_text(local_file, original_url)
full_text = None
doc = Document(gov_id=gov_id, release_date=release_date, add_date=add_date, title=title,
description=description, doc_type=doc_type, original_url=original_url,
local_file=local_file, full_text=full_text)
doc.save()
for bill_num in bill_list:
bill_dupe = DocumentLegislation.objects.filter(congress=congress).filter(bill_num=bill_num).filter(document=doc)
if not bill_dupe:
bill = DocumentLegislation(congress=congress, bill_num=bill_num, document=doc)
bill.save()
def handle_noargs(self, **options):
doc_type = "DPC LB"
file_type = "html"
add_date = datetime.datetime.now()
year = add_date.year
congress = congress_from_year(year)
url_prefix = "http://dpc.senate.gov/"
url = "%sdpcreports.cfm?cf_year=%s" % (url_prefix, year)
page = urllib2.urlopen(url)
soup = BeautifulSoup(page)
rows = soup.findAll('p', {"class": "doclist"})
for row in rows:
file_name = row('a')[0]['href'].strip()
p = re.compile('dpcdoc\.cfm\?doc_name=')
standard_format = p.findall(file_name)
if standard_format:
gov_id = file_name.replace('dpcdoc.cfm?doc_name=', '').upper()
else:
gov_id = None
original_url = "%s%s" % (url_prefix, file_name)
local_file = ''
title = row('a')[0].string
description = ''
bill_list = extract_legislation(title)
date_str = row.contents[3].string.replace('(', '').replace(')', '')
release_date = time.strftime('%Y-%m-%d',
time.strptime(date_str, '%m/%d/%y'))
doc = {
'original_url': original_url,
'local_file': local_file,
'title': title,
'description': description,
'bill_list': bill_list,
'release_date': release_date
}
print doc