def _get_matches_info(self, match_elements, championship_urls):
matches = []
base_len = len(OneXBetScraper._BASE_URL)
for match_element in list(match_elements)[:]:
try:
url = match_element.get_attribute('href')[base_len:]
except StaleElementReferenceException:
print('Caught StaleElementReferenceException')
continue
if url in championship_urls or match_element.get_attribute(
'class') != 'link' or url.endswith('-Special-bets/'):
continue
match_title_text = match_element.find_element_by_class_name(
'gname').text
match_title = MatchTitle.from_str(match_title_text)
date_time_str = match_element.find_element_by_class_name(
'date').text
try:
date_time = DateTime.from_1xbet_str(date_time_str)
except ValueError:
print(url)
continue
match = Match(match_title, self._BASE_URL + url, date_time, self)
matches.append(match)
return matches
def _get_match_title(tag):
"""
Scrapes match title found in the tag
:param tag: one of the tags in parsed document created from the championship url's html
:type tag: BeautifulSoup.Tag
:return: match title in the form 'first team - second_team'
:rtype: MatchTitle
"""
br = tag.find(class_='l').find('br')
teams = []
first_team = br.previous_sibling
if not isinstance(first_team, str):
first_team = first_team.text
teams.append(first_team)
second_team = br.next_sibling
if not isinstance(second_team, str) and second_team is not None:
second_team = second_team.text
if second_team:
teams.append(second_team)
match_title = MatchTitle(teams)
return match_title
def _get_bets_from_url(self, match_url):
"""
Scraps data such as match titles, bet titles and odds from the given match url
:param match_url: any match url on the website
:type match_url: str
:return: bets dictionary in the following form:
bets[match_title][bet_title] = odds
:rtype: dict
"""
self.renderer.get(match_url)
time.sleep(2)
bets = []
main_table = self.renderer.wait.until(
EC.presence_of_element_located(
(By.CLASS_NAME, 'Match__container___fpI_d')))
# main_table = self.renderer.find_element_by_class_name('Match__container___fpI_d')
teams = [
el.text for el in main_table.find_elements_by_class_name(
'__app-PromoMatchBody-competitor-name')
]
# print(teams)
try:
date = main_table.find_element_by_class_name(
'dateTime__date___2QS99').text.lower()
except Exception:
date = ''
match = Match(MatchTitle(teams), match_url, date)
self._parse_marketblocks(bets, match_url)
match.bets = bets
return match
def _get_bets_from_url(self, match_url):
self.renderer.get(match_url)
bets = []
basic_info = self.renderer.wait.until(
EC.presence_of_element_located(
(By.CLASS_NAME, 'sticky-inner-wrapper')))
# basic_info = self.renderer.find_element_by_class_name('sticky-inner-wrapper')
date = basic_info.find_element_by_class_name(
'event--date--1').text.lower()
date = self._format_date(date)
teams = [
el.text for el in basic_info.find_element_by_class_name(
'event--name').find_elements_by_tag_name('span')
]
match = Match(MatchTitle(teams), match_url, date, self)
element = self.renderer.wait.until(
EC.presence_of_element_located((By.CLASS_NAME, 'slick-block')))
element = self.renderer.wait.until(
EC.element_to_be_clickable((By.CLASS_NAME, 'slick-block')))
try:
self.renderer.click(element)
except Exception:
print('ne mogu nazhat na all')
time.sleep(0.5)
self._parse_marketblocks(bets, match_url)
match.bets = bets
return match
def _get_match_basic_data(self, match):
date_time_str = match.find_element_by_class_name('date').text
date_time = DateTime.from_marathon_str(date_time_str)
url = match.find_element_by_class_name('member-link').get_attribute(
'href')
teams = [
el.text for el in match.find_elements_by_tag_name('span')
if el.get_attribute('data-member-link')
]
return Match(MatchTitle(teams), url, date_time, self)
def _get_match_basic_data(self, event):
date = event.find_element_by_class_name('event--date').text
time = event.find_element_by_class_name('event--time').text
date_time_str = date + time
date_time = DateTime.from_favorit_str(date_time_str)
name = event.find_element_by_class_name('long--name').text.lower()
button = event.find_element_by_class_name('event--more')
self.renderer.click(button)
url = self.renderer.current_url
return Match(MatchTitle(name.split(' - ')), url, date_time, self)
def _get_live_match_basic_data(self, event):
teams = [el.text for el in event.find_elements_by_class_name('member')]
for team in teams:
if '—' in team:
teams.remove(team)
team = team.replace('—', '')
teams.append(team)
self.renderer.click(event)
url = self.renderer.current_url
self.renderer.back()
return Match(MatchTitle(teams), url, None, self)
def from_dict(cls, match_dict):
url = None
date_time = None
title = None
key = list(match_dict.keys())[0]
found = re.search(r'^(https://.+?) (.+?): (.+?)$', key)
if found:
url = found.group(1)
date_time = DateTime.fromisoformat(found.group(2))
title = MatchTitle.from_str(found.group(3))
bets_dict = list(match_dict.values())[0][0]
bets = [
Bet.from_dict({bet_title: odds})
for bet_title, odds in bets_dict.items()
]
return cls(title, url, date_time, None, bets)
def get_matches_info_sport(self, sport_name):
matches = []
subsections = self.get_tournaments(sport_name)
for subsection in subsections:
# if not LIVE:
try:
self.renderer.click(subsection)
except StaleElementReferenceException:
continue
# print(' ', subsections.index(subsection) + 1)
time.sleep(2)
events = self.renderer.find_elements_by_class_name(
'sportEventRow__body___3Ywcg')
time.sleep(2)
for event in events:
try:
event.find_element_by_class_name(
'matchDateTime__isLive___8f4IP')
continue # match is live
except NoSuchElementException:
pass
except StaleElementReferenceException:
continue
date_text = event.find_element_by_class_name(
'matchDateTime__date___2Hw-c').text
teams_webel = event.find_elements_by_class_name(
'__app-LogoTitle-wrapper')
teams = [el.text for el in teams_webel]
url = teams_webel[0].find_element_by_tag_name(
'a').get_attribute('href')
date = DateTime.from_ggbet_str(date_text)
matches.append(Match(MatchTitle(teams), url, date, self))
# if not LIVE:
self.renderer.click(subsection)
print(len(matches))
return Sport(sport_name, matches)
while True:
s = SequenceMatcher(None, first_team, second_team)
substring = s.find_longest_match(0, len(first_team), 0,
len(second_team))
if substring.size < min(3, min_initial_length):
break
substrings_total_length += substring.size
# print(first_team[substring.a:substring.b])
first_team = first_team[:substring.a] + first_team[substring.a +
substring.size:]
second_team = second_team[:substring.
b] + second_team[substring.b +
substring.size:]
similarity = substrings_total_length / min_initial_length + \
(substrings_total_length - max_initial_length) / (10 * max_initial_length)
return similarity
if __name__ == '__main__':
certainty = 0.5
comparator = MatchComparator()
m1 = Match(MatchTitle(['jd gaming', 'team we']), '123',
DateTime(2020, 12, 26, 12, 30), 1, [])
m2 = Match(MatchTitle(['jd', 'we']), '321', DateTime(2020, 12, 26, 13), 2,
[])
similarity = comparator.calculate_matches_similarity(m1, m2, certainty)
print(similarity)
print(comparator.similar(m1, m2, certainty))
print(comparator.similarities)
class GGBetScraper:
def __new__(cls):
if not hasattr(cls, 'instance'):
cls.instance = super(GGBetScraper, cls).__new__(cls)
return cls.instance
def get_name(self):
return '1xbet'
if __name__ == '__main__':
grouper = CSGOForkGrouper()
csgo = Sport('csgo', [
Match(
MatchTitle(['Top Esports', 'Suning Gaming']),
'https://1x-bet.com/en/line/Esports/1309773-League-of-Legends-LPL-Summer-Playoffs/81469989-Top-Esports-Suning-Gaming/',
DateTime(2020, 8, 9, 19, 0, 0), OneXBetScraper(), []),
Match(MatchTitle(['Top', 'Sunning']),
'https://www.parimatch.com/en/sport/kibersport/liga-legend-lpl',
DateTime(2020, 8, 9, 19, 0, 0), ParimatchScraper(), []),
Match(
MatchTitle(['Top Esports', 'SN Gaming']),
'https://www.favorit.com.ua/en/bets/#event=27802672&tours=182350,776347,776418,792747,977780,1011803,1037535,1061879,1258082,1265594,1293917,1618224,1713907,2270463',
DateTime(2020, 8, 9, 19, 0, 0), FavoritScraper(), []),
Match(
MatchTitle(['Suning Gaming', 'Top Esports']),
'https://www.marathonbet.com/en/betting/e-Sports/LoL/LPL+Summer/Main+Event/Best+of+5+maps/Suning+Gaming+vs+Top+Esports+-+9994779',
DateTime(2020, 8, 9, 19, 0, 0), MarathonScraper(), []),
Match(
MatchTitle(['Top Esports', 'Suning Gaming']),
def get_live_match_basic_data(self, event):
self.renderer.click(event)
teams = [name.text for name in event.find_elements_by_tag_name('span')]
match_url = self.renderer.current_url
return Match(MatchTitle(teams), match_url, '', self)