def get_pixelated_mug():
"""This function uploads the raw image to cloudinary and
then uploads the pixelated version to the airtable record."""
t0, i = time.time(), 0
needs_pix_img_formula = "AND(PHOTO != '', PIXELATED_IMG = '', hours_since_verification < 24, jail != 'jcdc')"
records = airtab.get_all(formula=needs_pix_img_formula)
for record in records:
this_dict = {}
url = record["fields"]["PHOTO"][0]["url"]
r = requests.get(url)
content_type = r.headers['Content-Type']
# print(content_type)
if content_type == 'image/jpeg':
try:
upload_response = uploader.upload(url,
opacity=40,
effect="blur:400")
time.sleep(1)
this_dict["PIXELATED_IMG"] = [{
"url":
upload_response['secure_url']
}]
airtab.update(record['id'], this_dict)
except cloudinary.exceptions.Error as err1:
print("cloudinary can't accept that shit: ", err1)
except AttributeError as err2:
print('Attribute Error for cloudinary upload: ', err2)
else:
print('this shit was some really weird content type:',
content_type)
wrap_it_up(t0, new=i, total=len(records), function='get_pixelated_mug')
def update_record(this_dict, soup, m, lea_parser=None, raw_lea=''):
if this_dict['recent_text'] != m['fields']['recent_text']:
this_dict['updated'] = True
this_dict['html'] = soup.prettify()
if lea_parser:
lea_parser(raw_lea)
airtab.update(m['id'], this_dict, typecast=True)
def retry_getting_mugshot():
t0, i = time.time(), 0
needs_pic_formula = "AND(PHOTO = '', hours_since_verification < 12, jail != 'lcdc')"
records = airtab.get_all(formula=needs_pic_formula)
print("we're gonna retry getting mugs for", len(records), "records...")
for record in records:
this_dict = {}
r = requests.get(record['fields']['link'])
if record['fields']['jail'] == 'jcdc':
soup = BeautifulSoup(r.text, 'html.parser').find(id='cms-content')
img_tag = soup.find('div', class_='inmate_profile_image').img
if img_tag['alt'] != 'Image Not Availble':
this_dict[
'img_src'] = f"https://www.jonesso.com/{img_tag['src']}"
this_dict['PHOTO'] = [{'url': this_dict['img_src']}]
# else:
# print('image not currently available')
elif record['fields']['jail'] == 'hcdc':
soup = BeautifulSoup(r.text, 'html.parser')
try:
img_src = 'http://www.co.hinds.ms.us' + soup.find(
'img', {'align': 'middle'})['src']
if requests.get(
img_src).headers['Content-Type'] == 'image/jpeg':
this_dict['img_src'] = img_src
this_dict['PHOTO'] = [{'url': img_src}]
else:
print('image source isn\'t actually an image')
except TypeError:
print('no img tag in intake html')
elif record['fields']['jail'] == 'kcdc':
soup = BeautifulSoup(r.text, 'html.parser').find(id='cms-content')
try:
img_tag = soup.find('img')
except AttributeError:
# print('no img tag in intake html')
continue
if soup.img:
img_src_raw = soup.img['src']
if img_src_raw.startswith(
'templates/kempercountysheriff.com/images/inmates'):
this_dict[
'img_src'] = f"https://www.kempercountysheriff.com/{img_src_raw}"
this_dict['PHOTO'] = [{'url': this_dict['img_src']}]
elif record['fields']['jail'] == 'acdc':
soup = BeautifulSoup(r.text, 'html.parser').find(
'div', class_='blog-content-container')
try:
img_tag = soup.find('img')
this_dict['img_src'] = img_tag.get('src')
this_dict['PHOTO'] = [{'url': this_dict['img_src']}]
except AttributeError:
# print('no img tag in intake html')
continue
else:
print(
f"awww hell... this one is from the {record['fields']['jail']} docket/scraper..."
)
airtab.update(record['id'], this_dict)
wrap_it_up(t0, new=i, total=len(records), function='retry_getting_mugshot')
def get_all_intake_deets():
t0, i = time.time(), 0
jcadc_deets_formula = "AND(jail = 'jcadc', charges = '', recent_text != '')"
records = airtab.get_all(formula=jcadc_deets_formula, fields='recent_text')
for record in records:
charges = []
bond_ammts = []
classifications = []
this_dict = {}
txt_str = record['fields']['recent_text']
chunks = txt_str.split('\nRequest Victim Notification\n')
match_1 = re.search(r"(\w+)\s+(Male|Female)", chunks[0])
try:
raw_race = match_1.group(1)
if raw_race == 'AVAILABLE':
this_dict['race'] = 'U'
else:
this_dict['race'] = raw_race[0]
this_dict['sex'] = match_1.group(2)[0]
except AttributeError:
print('there isnt race/sex info')
try:
this_dict['intake_weight'] = re.search(r"(\d+) Pounds",
chunks[0]).group(1)
except AttributeError:
print('there isnt weight info')
try:
this_dict['intake_height'] = re.search(r"(\d Ft. \d+ In.)",
chunks[0]).group(1)
except AttributeError:
print('idk how tall this person is')
try:
this_dict['intake_eye'] = re.search(r"(\w+)\s+Eyes",
chunks[0]).group(1)
except AttributeError:
print('eye color is a mystery')
this_dict['intake_age'] = re.search(r"(\d\d) Years Old",
chunks[0]).group(1)
crim_details = chunks[1].splitlines()
for ln in crim_details:
results = re.search(r"([MF]\w+) - Bond: (\$.*)", ln)
if results:
bond_ammts.append(results.group(2))
classifications.append(results.group(1))
elif ', ' in ln:
charges.append(f"\"{ln}\"")
else:
charges.append(ln)
this_dict['charges'] = ', '.join(charges)
this_dict['bond_ammounts'] = '\n'.join(bond_ammts)
this_dict['charge_classifications'] = ', '.join(classifications)
airtab.update(record['id'], this_dict, typecast=True)
i += 1
wrap_it_up(t0, new=i, total=len(records), function='get_all_intake_deets')
def pdf_to_dc(quiet=True):
# filters for recently verified intakes w/out dc_id.
# for records meeting that criteria, create pdf & store locally
t0, i = time.time(), 0
for jail in jails_lst:
if not quiet:
print(f"checking {jail[0]}. . .")
output_path = os.path.join("output", jail[0])
try:
ensure_dir(output_path)
except NotADirectoryError as err:
print(f"Skipping {jail[0]}: {err}")
continue
for fn in glob.glob(os.path.join(output_path, '*.pdf')):
if not quiet:
print(f"uploading {fn} . . .")
try:
obj = dc.documents.upload(fn)
except requests.exceptions.ReadTimeout:
time.sleep(7)
continue
obj = dc.documents.get(obj.id)
while obj.status != 'success':
time.sleep(7)
obj = dc.documents.get(obj.id)
obj.access = "public"
this_dict = {"jail": jail[0]}
obj.data = this_dict
obj.put()
this_dict["dc_id"] = str(obj.id)
print(f"successfully uploaded {obj.id}. . .")
this_dict["dc_title"] = obj.title
this_dict["dc_access"] = obj.access
this_dict["dc_pages"] = obj.pages
this_dict["PDF"] = obj.pdf_url
this_dict["dc_canonical_url"] = obj.canonical_url
this_dict["dc_resources_page_image"] = obj.normal_image_url
try:
full_text = obj.full_text.decode("utf-8")
except AttributeError as err:
full_text = obj.full_text
this_dict["dc_full_text"] = os.linesep.join([s for s in full_text.splitlines() if s])
# record = airtab.match(jail[1], this_dict["dc_title"], view='needs pdf')
record = airtab.match(jail[1], this_dict["dc_title"], sort=[('dc_id', 'asc'), ('initial_scrape', 'desc')])
airtab.update(record["id"], this_dict, typecast=True)
if jail[0] == 'lcdc':
os.rename(fn, f'/Users/blakefeldman/code/daily-journal-jail-data/pdfs/lee/{this_dict["dc_title"]}.pdf')
else:
send2trash.send2trash(fn)
i += 1
time.sleep(7)
wrap_it_up(t0, new=i, total=i, function='pdf_to_dc')
def get_full_text():
t0, i = time.time(), 0
records = airtab.get_all(formula="AND(dc_id != '', dc_full_text = '')",
fields=['dc_id'])
for record in records:
this_dict = {}
obj = dc.documents.get(record['fields']['dc_id'])
this_dict["dc_title"] = obj.title
this_dict["dc_access"] = obj.access
this_dict["dc_pages"] = obj.pages
this_dict["dc_full_text"] = obj.full_text.decode("utf-8")
airtab.update(record["id"], this_dict)
i += 1
wrap_it_up(t0, new=i, total=len(records), function='get_full_text')
def update_dc_fields():
records = airtab.get_all(view='need dc urls updated',
fields='dc_id',
max_records=100)
print(len(records), ' records need updated documentcloud URLs.')
for record in records:
this_dict = {}
dc_id = record['fields'].get('dc_id')
obj = dc.documents.get(dc_id)
this_dict["PDF"] = obj.pdf_url
this_dict["dc_canonical_url"] = obj.canonical_url
this_dict["dc_resources_page_image"] = obj.normal_image_url
airtab.update(record['id'], this_dict)
time.sleep(.3)
def update_summary(this_many=150):
"""This function updates the record summary. The reason we have this field,
rather than just use the 'blurb' field, is bc the gallery view works better
with a text field than it does with a formula field. Because this view will
regularly be packed full of records, the default max records is 100."""
t0, i = time.time(), 0
# outdated_summary_formula = "AND(blurb != '#ERROR!', blurb != summary)"
# records = airtab.get_all(formula=outdated_summary_formula, fields="blurb", max_records=this_many)
records = airtab.get_all(view='needs updated summary',
fields="blurb",
max_records=this_many)
for record in records:
this_dict = {}
this_dict["summary"] = record["fields"]["blurb"]
airtab.update(record["id"], this_dict)
wrap_it_up(t0, new=i, total=len(records), function='update_summary')
def remove_weird_character():
t0, i = time.time(), 0
remove_wierd_character_formula = "AND(hours_since_verification > 12, FIND('ã', recent_text) > 1)"
records = airtab.get_all(formula=remove_wierd_character_formula,
fields='recent_text')
for record in records:
this_dict = {}
x = record['fields']['recent_text'].find('ã')
y = record['fields']['recent_text'].find('\n', x)
this_dict['recent_text'] = record['fields']['recent_text'].replace(
record['fields']['recent_text'][x:y], '')
airtab.update(record['id'], this_dict)
i += 1
wrap_it_up(t0,
new=i,
total=len(records),
function='remove_weird_character')
def fix_charges_to_by_lines():
t0, i = time.time(), 0
records = airtab.get_all(
formula="AND(TEST_FORMULA != '', TEST_RESULT = '')", fields='charges')
for record in records:
this_dict = {}
cleaner = []
mess = record['fields']['charges'].replace('", ', '"\n').replace(
', "', '\n"').splitlines()
for c in mess:
if c.startswith('"'):
cleaner.append(c.replace('"', ''))
else:
for d in c.split(', '):
cleaner.append(d)
this_dict['TEST_RESULT'] = '\n'.join(cleaner)
airtab.update(record['id'], this_dict)
i += 1
wrap_it_up(t0,
new=i,
total=len(records),
function='fix_charges_to_by_lines')
def get_dor_if_possible(this_many=50):
t0, i = time.time(), 0
# records = airtab.get_all(view="check for DOR")
dor_formula = "AND(OR(jail = 'kcdc', jail = 'tcdc', jail = 'ccdc', jail = 'jcdc'), DOR = '', hours_since_verification > 6, hours_since_verification < 48)"
records = airtab.get_all(formula=dor_formula, max_records=this_many)
total = len(records)
for record in records:
this_dict = {}
try:
r = requests.get(record["fields"]["link"])
except requests.ConnectionError as err:
print(f"Skipping {record['fields']['link']}: {err}")
time.sleep(5)
continue
soup = BeautifulSoup(r.text, "html.parser")
data = []
for string in soup.stripped_strings:
data.append(str(string))
if "Release Date:" in data:
options = {
"quiet": "",
"footer-font-size": 10,
"footer-left": record["fields"]["link"],
"footer-right": time.strftime('%c'),
}
directory = f"./output/{record['fields']['jail']}/updated"
try:
ensure_dir(directory)
file_name = f"{record['fields']['bk']} (final).pdf"
fn = os.path.join(directory, file_name)
pdfkit.from_url(record["fields"]["link"], fn, options=options)
except NotADirectoryError as err:
print(f"Can't write PDF: {err}")
this_dict["DOR"] = datetime.datetime.strptime(
data[1 + data.index("Release Date:")], "%m-%d-%Y - %I:%M %p"
).strftime('%m/%d/%Y %H:%M')
airtab.update(record["id"], this_dict)
i += 1
wrap_it_up(t0, i, total, function='get_dor_if_possible')
def parse_charge_1():
t0, i = time.time(), 0
needs_charge_1_parsed_formula = "AND(OR(jail = 'mcdc', jail = 'prcdf'), charge_1_statute = '', hours_since_initial_scrape < 48, charge_1 != '', charge_1 != 'HOLDHOLD', charge_1 != 'DRUGDRUG COURT', charge_1 != 'HLD Other AgencyHold for other Agency')"
records = airtab.get_all(formula=needs_charge_1_parsed_formula)
for record in records:
this_dict = {}
x = None
if re.search("[)][A-Z]", record["fields"]["charge_1"]):
x = re.search("[)][A-Z]", record["fields"]["charge_1"])
elif re.search("[0-9][A-Z]", record["fields"]["charge_1"]):
x = re.search("[0-9][A-Z]", record["fields"]["charge_1"])
if x:
this_dict["charge_1_statute"] = record["fields"][
"charge_1"][:x.start() + 1]
this_dict["charge_1_title"] = record["fields"]["charge_1"][x.end(
) - 1:]
try:
airtab.update(record["id"], this_dict)
i += 1
except requests.exceptions.HTTPError as err:
print(err)
continue
wrap_it_up(t0, new=i, total=len(records), function='parse_charge_1')
def ccj_scraper():
t0, new_intakes, total_intakes = time.time(), 0, 0
main_url = 'http://www.calhounso.org/page.php?id=7'
r = requests.get(main_url, headers=muh_headers)
soup = BeautifulSoup(r.text, 'html.parser').find(id='cms_body_content')
try:
intakes = soup.table.tbody.find_all('td')
except AttributeError:
return
for intake in intakes:
total_intakes += 1
this_dict = {'jail': 'ccj'}
data = []
link = intake.find('a')
if link:
this_dict['link'] = link.get('href')
this_dict['bk'] = this_dict['link'].replace(
'http://www.vinelink.com/vinelink/servlet/SubjectSearch?siteID=25000&agency=18&offenderID=',
'')
for string in intake.stripped_strings:
if string.startswith('.') and string.endswith('.'):
pass
else:
data.append(str(string))
try:
get_name(data[0], this_dict)
except IndexError:
print('skipping empty td')
continue
raw_doi = data[1]
if raw_doi == date.today().strftime('%m/%d/%Y'):
this_dict['DOI'] = datetime.now().strftime('%m/%d/%Y %I:%M%p')
else:
this_dict['DOI'] = f"{raw_doi} 11:59pm"
remaining_data = ' '.join(data[2:])
DOR_index = remaining_data.find('Released')
if DOR_index != -1:
this_dict['charges'] = remaining_data[:DOR_index].strip()
raw_dor = remaining_data[DOR_index + 8:].strip()
if raw_dor == date.today().strftime('%m/%d/%Y'):
this_dict['DOR'] = datetime.now().strftime('%m/%d/%Y %I:%M%p')
else:
this_dict['DOR'] = f"{raw_dor} 12:01am"
else:
this_dict['charges'] = remaining_data
this_dict['recent_text'] = '\n'.join(data)
this_dict['html'] = intake.prettify()
this_dict['last_verified'] = (datetime.utcnow().replace(
tzinfo=timezone.utc).strftime('%m/%d/%Y %H:%M'))
m = airtab.match('recent_text', this_dict['recent_text'], view='ccj')
if not m:
airtab.insert(this_dict, typecast=True)
new_intakes += 1
else:
this_dict['updated'] = True
airtab.update(m['id'], this_dict, typecast=True)
time.sleep(0.2)
wrap_it_up(function='ccj_scraper',
t0=t0,
new=new_intakes,
total=total_intakes)
def jcadc_scraper():
t0, new_intakes, total_intakes = time.time(), 0, 0
root = 'https://services.co.jackson.ms.us/jaildocket'
r = requests.post(f"{root}/_inmateList.php?Function=count",
headers=muh_headers)
total_intakes = r.json()
last_page = int(total_intakes / 15)
pages = range(1, last_page + 1)
pages = list(pages)
random.shuffle(
pages
) # for some reason page 1 cannot be the first page visited sometimes
for pg in pages:
r = requests.post(
f"{root}/_inmateList.php?Function=list&Page={pg}&Order=BookDesc&Search=0",
headers=muh_headers)
try:
intakes = r.json()
except ValueError as err:
print(err)
continue
for intake in intakes:
data = []
this_dict = {'jail': 'jcadc', '_jail': ['recwShIgdZDcf4ZcJ']}
this_dict['bk'] = intake["Book_Number"]
this_dict['last_verified'] = (datetime.utcnow().replace(
tzinfo=timezone.utc).strftime('%m/%d/%Y %H:%M'))
this_dict['intake_number'] = intake["ID_Number"].strip()
this_dict[
'link'] = f"{root}/inmate/_inmatedetails.php?id={this_dict['intake_number']}"
r = requests.get(this_dict['link'], headers=muh_headers)
soup = BeautifulSoup(r.text, 'html.parser')
for string in soup.stripped_strings:
data.append(string)
this_dict['recent_text'] = '\n'.join(data[1:])
m = airtab.match('bk', this_dict['bk'])
if m:
airtab.update(m['id'], this_dict, typecast=True)
else:
raw_name = (
f"{intake['Name_First_MI']} {intake['Name_Middle']} "
f"{intake['Name_Last']} {intake['Name_Suffix']}")
get_name(raw_name, this_dict)
raw_doi = intake["BookDate"]
if raw_doi == date.today().strftime('%m/%d/%Y'):
this_dict['DOI'] = datetime.now().strftime(
'%m/%d/%Y %I:%M%p')
else:
this_dict['DOI'] = f"{raw_doi} 11:59pm"
this_dict['DOA'] = intake["ArrestDate"]
this_dict['LEA'] = standardize.jcadc_lea(
intake["Arrest_Agency"])
articles = soup.find_all('article')
this_dict['html'] = (
"<html>\n<body>\n"
f"{articles[0].prettify()}\n{articles[1].prettify()}\n"
"</body>\n</html>")
this_dict[
'img_src'] = f"{root}/inmate/{this_dict['intake_number']}.jpg"
this_dict['PHOTO'] = [{'url': this_dict['img_src']}]
airtab.insert(this_dict, typecast=True)
new_intakes += 1
wrap_it_up(function='jcadc_scraper',
t0=t0,
new=new_intakes,
total=total_intakes)
def jcj_scraper():
t0, new_intakes, total_intakes = time.time(), 0, 0
urls = [
'http://jasperso.com/inmate-roster/',
'http://jasperso.com/48-hour-release/'
]
for url in urls:
r = requests.get(url, headers=muh_headers)
soup = BeautifulSoup(r.text, 'html.parser').find('div', id='primary')
intakes = soup.find_all('div', class_='col-sm-4 inmate')
total_intakes += len(intakes)
for x in intakes:
this_dict = {'jail': 'jcj', '_jail': ['recwzuzsimZuPpVR5']}
get_name(x.h1.string.strip(), this_dict)
this_dict['link'] = url
data = []
for string in x.stripped_strings:
data.append(str(string))
this_dict['intake_number'] = data[1 + data.index('Arrest #:')]
this_dict['bk'] = data[1 + data.index('Arrest #:')]
raw_doi = data[1 + data.index('Arrest Date:')]
if raw_doi == date.today().strftime('%m/%d/%Y'):
this_dict['DOI'] = datetime.now().strftime('%m/%d/%Y %I:%M%p')
else:
this_dict['DOI'] = f"{raw_doi} 11:59pm"
if 'Release Date:' in data:
raw_dor = data[1 + data.index('Release Date:')]
if raw_dor == date.today().strftime('%m/%d/%Y'):
this_dict['DOR'] = datetime.now().strftime(
'%m/%d/%Y %I:%M%p')
else:
this_dict['DOR'] = f"{raw_dor} 12:01am"
this_dict['sex'] = data[1 + data.index('Gender:')].strip()[0:1]
this_dict['race'] = data[1 + data.index('Race:')].strip()[0:1]
this_dict['intake_age'] = int(data[1 + data.index('Age:')])
cleaned_charges = []
charges = data[1 + data.index('Charges:'):]
for charge in charges:
if ', ' in charge:
cleaned_charge = f"\"{charge}\""
else:
cleaned_charge = charge
cleaned_charges.append(cleaned_charge)
this_dict['charges'] = ', '.join(cleaned_charges)
this_dict['recent_text'] = '\n'.join(data)
this_dict['html'] = x.prettify()
this_dict['last_verified'] = (datetime.utcnow().replace(
tzinfo=timezone.utc).strftime('%m/%d/%Y %H:%M'))
raw_lea = data[1 + data.index('Arrest Agency:')]
m = airtab.match('bk', this_dict['bk'], view='jcj')
if not m:
this_dict['img_src'] = x.find('img').get('src')
this_dict['PHOTO'] = [{'url': this_dict['img_src']}]
this_dict['LEA'] = standardize.jcj_lea(raw_lea)
airtab.insert(this_dict, typecast=True)
new_intakes += 1
else:
if this_dict['recent_text'] != m['fields']['recent_text']:
this_dict['updated'] = True
this_dict['LEA'] = standardize.jcj_lea(raw_lea)
else:
pass
airtab.update(m['id'], this_dict, typecast=True)
time.sleep(0.2)
wrap_it_up(function='jcj_scraper',
t0=t0,
new=new_intakes,
total=total_intakes)
def hcdc_scraper():
t0, new_intakes, total_intakes = time.time(), 0, 0
main_url = 'http://www.co.hinds.ms.us/pgs/apps/inmate/inmate_list.asp'
try:
r = requests.get(main_url)
except requests.ConnectionError as err:
print(f"Skipping {main_url}: {err}")
time.sleep(5)
return
if r.status_code == 500:
print(r.text)
return
soup1 = BeautifulSoup(r.text, 'html.parser')
total_pages = int(soup1.h3.string.split()[3])
pages = list(range(1, total_pages + 1))
for page in pages:
param_str = f"name_sch=Date&SS1=1&ScrollAction=Page+{page}"
r = requests.get(f"{main_url}?{param_str}")
soup2 = BeautifulSoup(r.text, 'html.parser')
rows = soup2.find_all('tr')
for row in rows:
cells = row.find_all('td')
if len(cells) == 7:
total_intakes += 1
this_dict = {'jail': 'hcdc', '_jail': ['recJLBoeZlp4IYn4I']}
this_dict['bk'] = row.a.get('href').replace(
'inmate_detail.asp?ID=', '')
this_dict['last_verified'] = (datetime.utcnow().replace(
tzinfo=timezone.utc).strftime('%m/%d/%Y %H:%M'))
m = airtab.match('bk',
this_dict['bk'],
view='hcdc',
fields='recent_text')
if m:
airtab.update(m['id'], this_dict)
else:
this_dict['link'] = urllib.parse.urljoin(
main_url, row.a.get('href'))
try:
r = requests.get(this_dict['link'])
except requests.ConnectionError as err:
print(f"Skipping {this_dict['link']}: {err}")
time.sleep(5)
continue
intake_soup = BeautifulSoup(r.text, 'html.parser')
data = []
this_dict['html'] = intake_soup.find_all(
'table')[1].prettify()
for string in intake_soup.stripped_strings:
data.append(string)
try:
this_dict['recent_text'] = '\n'.join(
data[data.index('Name'):data.index('Disclaimer:')])
except ValueError:
this_dict['recent_text'] = ''
try:
get_name(data[1 + data.index('Name')], this_dict)
this_dict['intake_address_line_1'] = data[
1 + data.index('Address')]
this_dict['intake_address_line_2'] = data[
2 + data.index('Address')]
this_dict['DOB'] = data[1 +
data.index('Date of Birth')]
this_dict['sex'] = data[1 + data.index('Sex')]
if data[1 + data.index('Race')] != 'Height':
this_dict['race'] = data[1 + data.index('Race')]
raw_doi = data[1 + data.index('Arrest Date')]
if raw_doi == date.today().strftime('%m/%d/%Y'):
this_dict['DOI'] = datetime.now().strftime(
'%m/%d/%Y %I:%M%p')
elif raw_doi == '//':
pass
else:
this_dict['DOI'] = f"{raw_doi} 11:59pm"
raw_lea = data[1 + data.index('Arresting Agency')]
this_dict['LEA'] = standardize.hcdc_lea(raw_lea)
this_dict['charge_1'] = data[1 +
data.index('Charge 1')]
except ValueError as err:
print(err, f"({this_dict['link']})")
try:
img_src = urllib.parse.urljoin(
main_url,
intake_soup.find('img',
{'align': 'middle'})['src'])
if requests.get(img_src).headers[
'Content-Type'] == 'image/jpeg':
this_dict['img_src'] = img_src
this_dict['PHOTO'] = [{'url': img_src}]
else:
print('image source isn\'t actually an image')
except TypeError:
print('no pic at this time')
airtab.insert(this_dict, typecast=True)
new_intakes += 1
wrap_it_up(function='hcdc_scraper',
t0=t0,
new=new_intakes,
total=total_intakes)
def get_charges_from_recent_text():
"""This function parces the recent text field and extracts the listed charges."""
t0, i = time.time(), 0
needs_charges_formula = "AND(charges_updated = '', html != '', recent_text != '', hours_since_verification < 72, DONT_DELETE != 'no charges')"
records = airtab.get_all(formula=needs_charges_formula)
for record in records:
this_dict = {}
if record["fields"]["jail"] == "lcdc":
charges = []
bond_ammounts = []
fine_ammounts = []
soup = BeautifulSoup(record["fields"]["html"], "html.parser").tbody
rows = soup.find_all("tr")
if soup.tfoot:
goods = rows[:len(rows) - 1]
this_dict["intake_bond_cash"] = soup.tfoot.find_all(
"td")[2].b.string.strip()
this_dict["intake_fine_ammount"] = soup.tfoot.find_all(
"td")[3].b.string.strip()
else:
goods = rows
for row in goods:
cells = row.find_all("td")
if cells[0].string.strip():
if "," in cells[0].string.strip():
charges.append('"' + cells[0].string.strip() + '"')
else:
charges.append(cells[0].string.strip())
if cells[2].string.strip():
bond_ammounts.append(cells[2].string.strip().replace(
",", ""))
if cells[3].string.strip():
fine_ammounts.append(cells[3].string.strip().replace(
",", ""))
if charges:
this_dict["charges"] = ", ".join(charges)
if bond_ammounts:
this_dict["bond_ammounts"] = "\n".join(bond_ammounts)
if fine_ammounts:
this_dict["fine_ammounts"] = "\n".join(fine_ammounts)
airtab.update(record["id"], this_dict, typecast=True)
i += 1
elif record["fields"]["jail"] == "kcdc":
charges = []
text = record["fields"]["recent_text"]
goods = text[text.find("Charges:"):text.find("Note:")].splitlines()
if len(goods) > 1:
for good in goods:
if "," in good:
charges.append('"' + good.strip() + '"')
else:
charges.append(good)
this_dict["charges"] = ", ".join(goods[1:])
airtab.update(record["id"], this_dict)
i += 1
elif record["fields"]["jail"] in {"ccdc", "tcdc", "jcdc"}:
charges = []
text = record["fields"]["recent_text"]
x = text.find("\nCharges:") + 9
y = text.find("\nBond:")
goods = text[x:y].strip().splitlines()
for line in goods:
if "," in line:
charges.append('"' + line + '"')
else:
charges.append(line)
this_dict["charges"] = ", ".join(charges)
airtab.update(record["id"], this_dict)
i += 1
elif record["fields"]["jail"] == "hcdc":
messy = []
goods = []
data = record["fields"]["recent_text"].splitlines()
messy.append(data[data.index("Charge 1") + 1].strip())
messy.append(data[data.index("Charge 2") + 1].strip())
messy.append(data[data.index("Charge 3") + 1].strip())
messy.append(data[data.index("Charge 4") + 1].strip())
for x in messy:
if not x.startswith("Felony / Misd"):
if "," in x:
goods.append('"' + x + '"')
else:
goods.append(x)
this_dict["charges"] = ", ".join(goods)
airtab.update(record["id"], this_dict)
i += 1
wrap_it_up(t0,
new=i,
total=len(records),
function='get_charges_from_recent_text')
