def __extract_matches_list_of_series(self):
soup = Common.get_soup_object(self.__series_link)
series_formats = \
soup.find('div', class_='cb-col-100 cb-col cb-nav-main cb-bg-white').find('div').text.split(".")[0]
match_info_elements = soup.find_all(
'div', class_='cb-col-60 cb-col cb-srs-mtchs-tm')
for match_info_element in match_info_elements:
match_title_tag = match_info_element.find(
'a', class_='text-hvr-underline')
match_venue_tag = match_info_element.find('div')
[match_outcome_text, match_outcome] = self.__extract_match_outcome(
match_info_element.find('a', class_='cb-text-link'))
[is_valid_match, match_id, match_link, match_format
] = self.__validate_match(match_title_tag, match_venue_tag,
match_outcome, series_formats)
if is_valid_match:
[match_winning_team,
win_margin] = Common.get_match_winning_team_and_margin(
match_outcome, match_outcome_text)
match_object = Match(match_id, match_title_tag.text,
match_format, match_venue_tag.text,
match_outcome,
Common.home_page + match_link,
match_winning_team, win_margin)
self.__matches_list.append(match_object)
def __extract_series_list_in_calender_year(self):
link = Common.home_page + "/cricket-scorecard-archives/" + str(self.year)
soup = Common.get_soup_object(link)
series_blocks = soup.find_all('a', class_='text-hvr-underline')
for index, series_block in enumerate(series_blocks):
series_link = series_block.get('href')
if ("cricket-series" in series_link) and Common.is_series_valid(series_link):
series_id = series_link.split("/")[2]
series_title = series_block.text # .split(",")[0]
series_link = Common.home_page + series_link
series_object = Series(series_id, series_title, self.year, series_link)
self.series_list.append(series_object)
def __extract_match_data(self, category):
link = self.link.replace("live-cricket-scores",
"live-cricket-scorecard")
soup = Common.get_soup_object(link)
if self.series is None:
self.series = self.__extract_series_object(soup, category)
self.format = Common.get_match_format(self.title, self.series.format)
if self.format is not None:
self.__extract_match_info(soup)
if self.__is_valid() is True:
self.__extract_teams(soup)
self.__extract_teams_short_names()
self.time = self.__get_match_time()
self.is_valid = True
def __init__(self, link, match_squad_ref):
self.__short_name_to_full_name_map = {}
self.__full_match_commentary = []
self.__per_innings_head_to_head_object_cache = [{}, {}, {}, {}]
# {"player_name" : "team_name", ......}
self.__local_squad = {}
for team in match_squad_ref:
for player in match_squad_ref[team]:
self.__local_squad[player] = team
soup = Common.get_soup_object(link)
commentary_blocks = soup.find_all('p', class_='cb-col cb-col-90 cb-com-ln')
for commentary_block in reversed(commentary_blocks):
ball_commentary = commentary_block.text.split(',')
self.__full_match_commentary.append(ball_commentary)
def __extract_match_info_squad_and_scores(self, series_squad_ref):
match_score_card_link = Common.home_page + "/api/html/cricket-scorecard/" + str(self.__id)
soup = Common.get_soup_object(match_score_card_link)
# Extract Match Info
self.__extract_match_info(soup)
# Extract Match Squad
self.__extract_match_squad(soup, series_squad_ref)
# Extract Per-Innings Scores
team_innings = soup.find_all('div', id=True)
for innings_num, innings_data in enumerate(team_innings):
innings_bat_bowl_blocks = innings_data.find_all('div', class_='cb-col cb-col-100 cb-ltst-wgt-hdr')
innings_batting_block = innings_bat_bowl_blocks[0]
innings_bowling_block = innings_bat_bowl_blocks[1]
innings_score_object = self.__extract_innings_total_score(innings_batting_block,
innings_num, self.__playing_teams)
innings_score_object.set_batting_scores(self.__extract_innings_batting_scores(innings_batting_block))
innings_score_object.set_bowling_scores(self.__extract_innings_bowling_scores(innings_bowling_block))
self.__innings_scores.append(innings_score_object)
def __extract_player_profile(self):
default_player_profile = {
'Role': '--',
'Batting Style': '--',
'Bowling Style': '--'
}
default_keys = default_player_profile.keys()
player_link = "http://www.cricbuzz.com/profiles/" + str(self.__id)
soup = Common.get_soup_object(player_link)
key_tags = soup.find_all(
'div', class_="cb-col cb-col-40 text-bold cb-lst-itm-sm")
value_tags = soup.find_all('div', "cb-col cb-col-60 cb-lst-itm-sm")
for key, val in zip(key_tags, value_tags):
key = key.text.strip()
if key in default_keys:
default_player_profile[key] = val.text.strip()
self.__role = default_player_profile['Role']
self.__batting_style = default_player_profile['Batting Style']
self.__bowling_style = default_player_profile['Bowling Style']
def __extract_schedule(self):
soup = Common.get_soup_object(
"https://www.cricbuzz.com/cricket-schedule/upcoming-series/")
category_blocks = soup.find_all('div', {
'class': 'cb-col-100 cb-col',
'ng-show': True
})
for category_block in category_blocks:
if category_block.next_element.text == self.date:
category_type = Common.get_category_type(
category_block.get('ng-show'))
series_blocks = category_block.find_all(
'div', class_='cb-col-100 cb-col')
for series_block in series_blocks:
series_title = series_block.next_element.text
series_object = None
if series_title in self.series_data:
series_object = self.series_data[series_title]
match_blocks = series_block.find_all(
'div', 'cb-ovr-flo cb-col-60 cb-col cb-mtchs-dy-vnu ')
if (match_blocks is None) or\
((match_blocks is not None) and (len(match_blocks) == 0)):
# Control comes here in case of multiple matches being played in single day of a series
match_blocks = series_block.find_all(
'div',
'cb-ovr-flo cb-col-60 cb-col cb-mtchs-dy-vnu cb-adjst-lst'
)
for match_block in match_blocks:
match_title_block = match_block.find('a', href=True)
match_title = match_title_block.text
match_link = Common.home_page + match_title_block.get(
'href')
match_venue = match_block.find('div').text
match_object = Match(match_title, match_venue,
match_link, series_object,
category_type)
if match_object.is_valid:
if series_object is None:
series_object = match_object.get_series_object(
)
self.series_data[series_title] = series_object
series_object.add_match(match_object)