def get_recruiting_timeline(player_id, player_profile_url, full_name):
recruiting_profile_html = http_get(f'{player_profile_url}/TimelineEvents')
base_page = BeautifulSoup(recruiting_profile_html, 'html.parser')
number_of_timeline_pages = 1
try:
number_of_timeline_pages = int(base_page.find_all('a', class_='pagn_link')[-2].text)
except:
print(emoji.emojize(f':warning: Couldn\'t parse pagination for {full_name}',
use_aliases=True))
event_output_list = []
timeline_ul = base_page.find('ul', class_='timeline-event-index_lst')
timeline_lis = timeline_ul.find_all('li')
for page in range(0, number_of_timeline_pages):
if page != 0:
recruiting_profile_html = http_get(f'{player_profile_url}/TimelineEvents/?page={page}')
base_page = BeautifulSoup(recruiting_profile_html, 'html.parser')
timeline_ul = base_page.find('ul', class_='timeline-event-index_lst')
timeline_lis = timeline_ul.find_all('li')
for list_item in timeline_lis:
event_output = {
'247_id': player_id
}
date_and_event_split = list_item.find('b').text.split(': ')
event_output['event_date'] = convert_to_year_month_day_from_word_month(date_and_event_split[0])
event_output['event_type'] = date_and_event_split[1]
paragraph_tags = list_item.find_all('p')
event_output['event_description'] = paragraph_tags[1].text
event_output_list.append(event_output)
return event_output_list
def get_ranking_history_url(player_profile_url, full_name):
html = http_get(player_profile_url)
base_page = BeautifulSoup(html, 'html.parser')
try:
return base_page.find('a', class_='rank-history-link')['href']
except:
print(emoji.emojize(f':thumbsdown: Error parsing recruiting ranking history page for {full_name}', use_aliases=True))
def get_number_of_pages_for_year(year, recruits_per_page):
url = f'https://247sports.com/Season/{year}-Football/CompositeRecruitRankings/'
html = http_get(url)
base_page = BeautifulSoup(html, 'html.parser')
count_span = base_page.find('span', class_='count')
recruit_count = int(count_span.text.strip(' ()'))
return math.ceil(recruit_count / recruits_per_page)
def get_recruiting_ranking_history(player_id, recruiting_ranking_url, full_name):
recruiting_ranking_html = http_get(recruiting_ranking_url)
base_page = BeautifulSoup(recruiting_ranking_html, 'html.parser')
recruiting_ranking_ul = base_page.find('ul', class_='ranking-history-list')
recruiting_ranking_lis = recruiting_ranking_ul.find_all('li', class_='')
ranking_history_output = []
for list_item in recruiting_ranking_lis:
try:
try:
rank_text = list_item.find('span', class_='rank').text
rank_value = float(rank_text) if rank_text != '-' else 0.0
except:
rank_value = -1.0
rating_text = list_item.find('span', class_='rating').text
rating_value = float(rating_text) if rating_text != '-' else 0.0
delta_element = list_item.find('span', class_='last')
delta_value = float(delta_element.text) if delta_element.text != '-' else 0.0
delta_value = delta_value * -1.0 if 'red' in delta_element['class'] else delta_value
delta_inception_element = list_item.find('span', class_='inception')
delta_inception_value = float(delta_inception_element.text) if delta_inception_element.text != '-' else 0.0
delta_inception_value = delta_inception_value * -1.0 if 'red' in delta_inception_element[
'class'] else delta_inception_value
ranking_history_output.append({
'247_id': player_id,
'rating': rating_value,
'rank': rank_value,
'change_date': convert_to_year_month_day_from_number_month(
list_item.find('span', class_='change-date').text),
'delta': delta_value,
'delta_inception': delta_inception_value
})
except:
print(emoji.emojize(f':thumbsdown: Error parsing ranking history for {full_name}', use_aliases=True))
return ranking_history_output
def parse_page_of_recruits(url, recruit_list, year):
html = http_get(url)
base_page = BeautifulSoup(html, 'html.parser')
rankings_page_div = base_page.find('div', class_='rankings-page__main')
list_items = rankings_page_div.find_all('li',
class_='rankings-page__list-item')
for list_item in list_items:
recruit = {}
name_link = list_item.find('a', class_='rankings-page__name-link')
if name_link is not None:
recruit = {
'247_id': name_link['href'].split('-')[-1],
'247_url': f'https://247sports.com{name_link["href"]}',
'full_name': name_link.text,
'year': year,
'position': list_item.find('div',
class_='position').text.strip()
}
meta_span_text = list_item.find('span', class_='meta').text
try:
high_school_and_hometown = re.findall(
'^([\w|\W+\s?]+)\((.*?)\)', meta_span_text)[0]
recruit['high_school'] = high_school_and_hometown[0].strip()
hometown_split = high_school_and_hometown[1].split(', ')
recruit['city'] = hometown_split[0]
recruit['state'] = hometown_split[1]
except:
recruit['high_school'] = ''
recruit['city'] = ''
recruit['state'] = ''
print(
emoji.emojize(
f':thumbsdown: Error parsing high school and hometown "{meta_span_text}" for {recruit["full_name"]}',
use_aliases=True))
ranking_div = list_item.find(
'div', class_='rankings-page__star-and-score')
recruit['score'] = ranking_div.find('span', class_='score').text
star_list = ranking_div.find_all('span',
class_='icon-starsolid yellow')
recruit['stars'] = len(star_list)
try:
height_and_weight_text = list_item.find(
'div', class_='metrics').text.strip()
height_and_weight_split = height_and_weight_text.split(' / ')
height_split = height_and_weight_split[0].split('-')
recruit['height_feet'] = float(height_split[0])
recruit['height_inches'] = float(height_split[1])
recruit['weight'] = float(height_and_weight_split[1])
except:
recruit['height_feet'] = 0.0
recruit['height_inches'] = 0.0
recruit['weight'] = 0.0
print(
emoji.emojize(
f':thumbsdown: Error parsing height, feet, and weight "{height_and_weight_text}" for {recruit["full_name"]}',
use_aliases=True))
recruit_list.append(recruit)