def wrangle_inmate_data_from_tag(rowtag):
d = {}
col = rowtag.select('td')
d['tdcj_id'] = col[0].text.strip()
d['url'] = make_absolute_url(col[1].select('a')[0].attrs['href'])
d['last_name'] = col[2].text.strip()
d['first_name'] = col[3].text.strip()
d['birthdate'] = txdate_to_iso(col[4].text.strip())
d['gender'] = col[5].text.strip()
d['race'] = col[6].text.strip()
d['date_received'] = txdate_to_iso(col[7].text.strip())
d['date_offense'] = txdate_to_iso(col[9].text.strip())
d['county'] = col[8].text.strip()
d['age_at_offense'] = round(
calc_years_diff(d['birthdate'], d['date_offense']))
d['years_before_death_row'] = calc_years_diff(d['date_offense'],
d['date_received'])
return d
def wrangle_inmate_data_from_tag(rowtag):
"""
Args:
rowtag: a BeautifulSoup <Tag> object, ostensibly representing a table row
from a parsed Texas death row HTML table, e.g.
<tr>
<td>999608</td>
<td align="center"><a href="dr_info/hudsonwilliam.html" title="Offender Information for William Hudson">Offender Information</a></td>
<td>Hudson</td>
<td>William</td>
<td>07/03/1982</td>
<td align="center">M</td>
<td>White</td>
<td>11/16/2017</td>
<td>Anderson</td>
<td>11/14/2015</td>
</tr>
Returns:
<dict>: A dictionary object that contains some of the values in
the HTML, with formatting where standardization is needed --
e.g. for dates and for the inmate's URL (absolute vs relative)
and some derived attributes, e.g. 'age_at_offense'
The value for 'url' should be an absolute URL, i.e. a valid
URL on the Web, not a relative one.
'birthdate', date_received', 'date_offense' should be in 'YYYY-MM-DD'
format
All values are strings except for:
'age_at_offense', which is an integer derived from birthdate and
date of offense
'years_before_death_row', which is a float
(rounded to nearest tenth) derived
from date of offense and date received, i.e.
number of years between commission of crime and entering
death row.
e.g.
{
'tdcj_id': '999608',
'url': 'https://wgetsnaps.github.io/tdcj-state-tx-us-2018/death_row/dr_info/hudsonwilliam.html',
'last_name': 'Hudson',
'first_name': 'William',
'birthdate': '1982-07-03',
'gender': 'M',
'race': 'White',
'date_received': '2017-11-16',
'date_offense': '2015-11-14',
'age_at_offence': 33,
'years_before_death_row': 2.0
}
"""
### fill in yourself
### (this one will be pretty long, though it's mostly tedious/repetitive steps)
cat_array = rowtag.select('td')
return_dict = {}
return_dict['tdcj_id'] = cat_array[0].text.strip()
return_dict['url'] = make_absolute_url(cat_array[1].select('a')[0].attrs['href'])
return_dict['last_name'] = cat_array[2].text
return_dict['first_name'] = cat_array[3].text
return_dict['birthdate'] = txdate_to_iso(cat_array[4].text)
return_dict['gender'] = cat_array[5].text
return_dict['race'] = cat_array[6].text
return_dict['date_received'] = txdate_to_iso(cat_array[7].text)
return_dict['county'] = cat_array[8].text.strip()
return_dict['date_offense'] = txdate_to_iso(cat_array[9].text)
return_dict['age_at_offense'] = int(calc_years_diff(return_dict['birthdate'], return_dict['date_offense'])) + 1
return_dict['years_before_death_row'] = calc_years_diff(return_dict['date_offense'], return_dict['date_received'])
return return_dict
def wrangle_inmate_data_from_tag(rowtag):
"""
Args:
rowtag: a BeautifulSoup <Tag> object, ostensibly representing a table row
from a parsed Texas death row HTML table, e.g.
<tr>
<td>999608</td>
<td align="center"><a href="dr_info/hudsonwilliam.html" title="Offender Information for William Hudson">Offender Information</a></td>
<td>Hudson</td>
<td>William</td>
<td>07/03/1982</td>
<td align="center">M</td>
<td>White</td>
<td>11/16/2017</td>
<td>Anderson</td>
<td>11/14/2015</td>
</tr>
Returns:
<dict>: A dictionary object that contains some of the values in
the HTML, with formatting where standardization is needed --
e.g. for dates and for the inmate's URL (absolute vs relative)
and some derived attributes, e.g. 'age_at_offense'
The value for 'url' should be an absolute URL, i.e. a valid
URL on the Web, not a relative one.
'birthdate', date_received', 'date_offense' should be in 'YYYY-MM-DD'
format
All values are strings except for:
'age_at_offense', which is an integer derived from birthdate and
date of offense
'years_before_death_row', which is a float
(rounded to nearest tenth) derived
from date of offense and date received, i.e.
number of years between commission of crime and entering
death row.
e.g.
{
'tdcj_id': '999608',
'url': 'https://wgetsnaps.github.io/tdcj-state-tx-us-2018/death_row/dr_info/hudsonwilliam.html',
'last_name': 'Hudson',
'first_name': 'William',
'birthdate': '1982-07-03',
'gender': 'M',
'race': 'White',
'date_received': '2017-11-16',
'date_offense': '2015-11-14',
'age_at_offence': 33,
'years_before_death_row': 2.0
}
"""
### fill in yourself
### (this one will be pretty long, though it's mostly tedious/repetitive steps)
offender_dict = {}
td_elements = rowtag.select('td')
#get id number and add to dictionary
offender_dict['tdcj_id'] = td_elements[0].text.strip()
#derive absolute url from relative, file under 'url'
url_line = rowtag.select('td a')
relative_url = url_line[0].attrs['href']
offender_dict['url'] = make_absolute_url(relative_url)
#get last name, first name
offender_dict['last_name'] = td_elements[2].text.strip()
offender_dict['first_name'] = td_elements[3].text.strip()
#get birthdate (add in 'YYYY-MM-DD' format)
birthdate = td_elements[4].text.strip()
iso_birthdate = txdate_to_iso(birthdate)
offender_dict['birthdate'] = iso_birthdate
#gender
gender = td_elements[5].text.strip()
offender_dict['gender'] = gender
#race
race = td_elements[6].text.strip()
offender_dict['race'] = race
#get the date sentence received ('YYYY-MM-DD' format)
date_received = txdate_to_iso(td_elements[7].text)
offender_dict['date_received'] = date_received
#get the date of the offense ('YYYY-MM-DD' format)
date_of_offense = txdate_to_iso(td_elements[-1].text.strip())
offender_dict['date_offense'] = date_of_offense
#calculate age at offense and store as integer value
age = calc_years_diff(iso_birthdate, date_of_offense) + 1
offender_dict['age_at_offense'] = int(age)
#determine years before death row
years_before = calc_years_diff(date_of_offense, date_received)
offender_dict['years_before_death_row'] = years_before
#county
county = td_elements[-2].text.strip()
offender_dict['county'] = county
#give you the dictionary with each element
return offender_dict
def wrangle_inmate_data_from_tag(rowtag):
"""
Args:
rowtag: a BeautifulSoup <Tag> object, ostensibly representing a table row
from a parsed Texas death row HTML table, e.g.
<tr>
<td>999608</td>
<td align="center"><a href="dr_info/hudsonwilliam.html" title="Offender Information for William Hudson">Offender Information</a></td>
<td>Hudson</td>
<td>William</td>
<td>07/03/1982</td>
<td align="center">M</td>
<td>White</td>
<td>11/16/2017</td>
<td>Anderson</td>
<td>11/14/2015</td>
</tr>
Returns:
<dict>: A dictionary object that contains some of the values in
the HTML, with formatting where standardization is needed --
e.g. for dates and for the inmate's URL (absolute vs relative)
and some derived attributes, e.g. 'age_at_offense'
The value for 'url' should be an absolute URL, i.e. a valid
URL on the Web, not a relative one.
'birthdate', date_received', 'date_offense' should be in 'YYYY-MM-DD'
format
All values are strings except for:
'age_at_offense', which is an integer derived from birthdate and
date of offense
'years_before_death_row', which is a float
(rounded to nearest tenth) derived
from date of offense and date received, i.e.
number of years between commission of crime and entering
death row.
e.g.
{
'tdcj_id': '999608',
'url': 'https://wgetsnaps.github.io/tdcj-state-tx-us-2018/death_row/dr_info/hudsonwilliam.html',
'last_name': 'Hudson',
'first_name': 'William',
'birthdate': '1982-07-03',
'gender': 'M',
'race': 'White',
'date_received': '2017-11-16',
'county': 'Anderson',
'date_offense': '2015-11-14',
'age_at_offence': 33,
'years_before_death_row': 2.0
}
"""
def get_text(num):
return td_tags[num].text.strip()
td_tags = rowtag.select('td')
date_offense = txdate_to_iso(get_text(9))
birth_date = txdate_to_iso(get_text(4))
date_received = txdate_to_iso(get_text(7))
dict = {
'tdcj_id': get_text(0),
'url': make_absolute_url(td_tags[1].select('a')[0].attrs['href']),
'last_name': get_text(2),
'first_name': get_text(3),
'birthdate': birth_date,
'gender': get_text(5),
'race': get_text(6),
'date_received': date_received,
'county': get_text(8),
'date_offense': date_offense,
'age_at_offense': round(calc_years_diff(birth_date, date_offense)),
'years_before_death_row': calc_years_diff(date_offense, date_received)
}
return dict
def test_half_year():
assert calc_years_diff('2017-07-01', '2018-01-01') == 0.5
def test_decade_diff():
assert calc_years_diff('2002-05-01', '2012-05-01') == 10
def test_zero_diff():
assert calc_years_diff('2012-01-01', '2012-01-01') == 0
def test_return_type():
assert isinstance(calc_years_diff('2012-01-01', '2015-05-05'), float)
