def _populate(self):
"""Returns information about a specific brewery.
Args:
url (string): The specific url of the beer. Looks like:
"/brewers/new-belgium-brewing-company/77/"
Returns:
A dictionary of attributes about that brewery."""
soup = soup_helper._get_soup(self.url)
try:
s_contents = soup.find(
'div',
id='container').find('table').find_all('tr')[0].find_all('td')
except AttributeError:
raise rb_exceptions.PageNotFound(self.url)
self.name = soup.h1.text
self.type = re.findall(r'Type: (.*?)<br\/>',
soup.decode_contents())[0].strip()
if soup.find_all(string='Web: '):
self.web = soup.find_all(string='Web: ')[0].find_next()['href']
self.telephone = Brewery._find_span(s_contents[0], 'telephone')
self.street = Brewery._find_span(s_contents[0], 'streetAddress')
self.city = Brewery._find_span(s_contents[0], 'addressLocality')
self.state = Brewery._find_span(s_contents[0], 'addressRegion')
self.country = Brewery._find_span(s_contents[0], 'addressCountry')
self.postal_code = Brewery._find_span(s_contents[0], 'postalCode')
self._has_fetched = True
return self
def _populate(self):
"""Returns information about a specific brewery.
Args:
url (string): The specific url of the beer. Looks like:
"/brewers/new-belgium-brewing-company/77/"
Returns:
A dictionary of attributes about that brewery."""
soup = soup_helper._get_soup(self.url)
s_contents = soup.find_all(
'div', {'itemtype': 'http://schema.org/LocalBusiness'})
if not s_contents:
raise rb_exceptions.PageNotFound(self.url)
self.name = soup.h1.text
self.type = s_contents[0].find_all('div')[1].text.strip()
website = s_contents[0].find_all(
'div', {'class': 'media-links'})[0].find_all('a')[0]
if website:
self.web = website['href']
self.telephone = Brewery._find_span(s_contents[0], 'telephone')
self.street = Brewery._find_span(s_contents[0], 'streetAddress')
self.city = Brewery._find_span(s_contents[0], 'addressLocality')
self.state = Brewery._find_span(s_contents[0], 'addressRegion')
self.country = Brewery._find_span(s_contents[0], 'addressCountry')
self.postal_code = Brewery._find_span(s_contents[0], 'postalCode')
self._has_fetched = True
return self
def _get_soup(url):
if _BASE_URL in url:
url.replace(_BASE_URL, "")
req = requests.get(_BASE_URL + url, allow_redirects=True)
if "ratebeer robot oops" in req.text.lower():
raise rb_exceptions.PageNotFound(url)
return BeautifulSoup(req.text, "lxml")
def _get_soup(url):
if _BASE_URL in url:
url.replace(_BASE_URL, '')
req = requests.get(_BASE_URL + url, allow_redirects=True)
if '<meta http-equiv="Content-Type" content="text/html;" charset="utf-8">' in req.text:
req.encoding = 'utf-8'
if "ratebeer robot oops" in req.text.lower():
raise rb_exceptions.PageNotFound(url)
return BeautifulSoup(req.text, "lxml")
def _populate(self):
soup = soup_helper._get_soup(self.url)
# check for 404s
try:
soup_rows = soup.find('div',
id='container').find('table').find_all('tr')
except AttributeError:
raise rb_exceptions.PageNotFound(self.url)
# ratebeer pages don't actually 404, they just send you to this weird
# "beer reference" page but the url doesn't actually change, it just
# seems like it's all getting done server side -- so we have to look
# for the contents h1 to see if we're looking at the beer reference or
# not
# if "beer reference" in soup_rows[0].find_all('td')[1].h1.contents:
# raise rb_exceptions.PageNotFound(self.url)
# if "Also known as " in soup_rows[1].find_all('td')[1].div.div.contents:
# raise rb_exceptions.AliasedBeer(self.url, soup_rows[1].find_all('td')[1].div.div.a['href'])
if soup_rows is None:
raise rb_exceptions.PageNotFound(self.url)
# General information from the top of the page
self.name = soup.find(itemprop='name').text.strip()
breweries = soup.find_all('a', href=re.compile('brewers'))
self.brewery = Brewery(breweries[1].get('href'))
self.brewery.name = breweries[1].text
if len(breweries) == 3:
self.brewed_at = Brewery(breweries[2].get('href'))
self.brewed_at.name = breweries[2].text
else:
self.brewed_at = None
try:
self.overall_rating = int(
soup.find('span',
text='overall').next_sibling.next_sibling.text)
except ValueError: # 'n/a'
self.overall_rating = None
except AttributeError:
self.overall_rating = None
try:
self.style_rating = int(
soup.find('span',
text='style').previous_sibling.previous_sibling)
except ValueError: # 'n/a'
self.style_rating = None
except AttributeError:
self.style_rating = None
self.style = soup.find(text='Style: ').next_sibling.text
self.style_url = soup.find(text='Style: ').next_sibling.get('href')
self.img_url = soup.find(id="beerImg").get('src')
# Data from the info bar
self.num_ratings = int(soup.find('span', itemprop="ratingCount").text)
try:
self.mean_rating = float(
soup.find(text='MEAN: ').next_sibling.text.split('/')[0])
except ValueError: # Empty mean rating: '/5.0'
self.mean_rating = None
except AttributeError: # No mean rating
self.mean_rating = None
try:
self.weighted_avg = float(
soup.find(attrs={
"name": "real average"
}).find('span', itemprop="ratingValue").text)
except ValueError: # Empty weighted average rating: '/5'
self.weighted_avg = None
except AttributeError: # No weighted average rating
self.weighted_avg = None
try:
self.seasonal = soup.find(
text=u'\xa0\xa0 SEASONAL: ').next_sibling.text
except AttributeError:
self.seasonal = None
try:
self.ibu = int(
soup.find(
title="International Bittering Units - Normally from hops"
).next_sibling.next_sibling.text)
except AttributeError:
self.ibu = None
try:
self.calories = int(
soup.find(
title="Estimated calories for a 12 fluid ounce serving").
next_sibling.next_sibling.text)
except AttributeError:
self.calories = None
try:
self.abv = float(
soup.find(title="Alcohol By Volume").next_sibling.next_sibling.
text[:-1])
except ValueError: # Empty ABV: '-'
self.abv = None
if soup.find(title="Currently out of production"):
self.retired = True
else:
self.retired = False
# Description
description = soup.find('div', 'commercial-description-container')
if 'no commercial description' not in description.text.lower():
# strip ads
[s.extract() for s in description('small')]
self.description = ' '.join([s for s in description.strings
]).strip()
self.tags = [
t.text[1:] for t in soup.find_all('span', class_="tagLink")
]
self._has_fetched = True
return self
def _populate(self):
soup = soup_helper._get_soup(self.url)
# check for 404s
try:
soup_rows = soup.find('div',
id='container').find('table').find_all('tr')
except AttributeError:
raise rb_exceptions.PageNotFound(self.url)
# ratebeer pages don't actually 404, they just send you to this weird
# "beer reference" page but the url doesn't actually change, it just
# seems like it's all getting done server side -- so we have to look
# for the contents h1 to see if we're looking at the beer reference or
# not
if "beer reference" in soup_rows[0].find_all('td')[1].h1.contents:
raise rb_exceptions.PageNotFound(self.url)
if "Also known as " in soup_rows[1].find_all('td')[1].div.div.contents:
raise rb_exceptions.AliasedBeer(
self.url, soup_rows[1].find_all('td')[1].div.div.a['href'])
# get beer meta information
# grab the html and split it into a keyword and value
brew_info_html = soup_rows[1].find_all('td')[1].div.small
brew_info = [
s.split(': ') for s in brew_info_html.text.split(u'\xa0\xa0')
]
keyword_lookup = {
"RATINGS": "num_ratings",
"MEAN": "mean_rating",
"WEIGHTED AVG": "weighted_avg",
"SEASONAL": "seasonal",
"CALORIES": "calories",
"EST. CALORIES": "calories",
"ABV": "abv",
"IBU": "ibu",
}
# match the data pulled from the brew info and match it to they keyword
# in the lookup table
for meta_name, meta_data in brew_info:
match = keyword_lookup.get(meta_name.strip())
if match == "mean":
meta_data = meta_data[:meta_data.find("/")]
elif match == "abv":
meta_data = meta_data[:-1]
elif not match:
continue
# convert to float if possible
try:
if match == "num_ratings":
meta_data = int(meta_data)
else:
meta_data = float(meta_data)
except ValueError:
pass
setattr(self, match, meta_data)
info = soup_rows[1].tr.find_all('td')
# get basic brewery information
brewery_info = info[1].find('div').contents
brewery_urls = brewery_info[0].findAll('a')
brewery = brewery_urls[0]
brewed_at = None
if len(brewery_urls) == 2:
brewed_at = brewery_urls[1]
if brewery:
self.brewery = brewery.text.strip()
self.brewery_url = brewery.get('href')
if brewed_at:
self.brewed_at = brewed_at.text.strip()
self.brewed_at_url = brewed_at.get('href')
# get ratings
ratings = info[0].findAll('div')
if len(ratings) > 3:
self.overall_rating = ratings[1].contents[2]
self.style_rating = ratings[3].contents[0]
# get the beer style
if brewery_info[3]:
self.style = brewery_info[3].text.strip()
# get the beer country
if ',' in brewery_info[5]:
# Non-USA addresses
self.brewery_country = brewery_info[5].split(',')[1].strip()
else:
# USA addresses
self.brewery_country = brewery_info[8].strip()
# get the beer description
description = soup_rows[1].find_all('td')[1].find(
'div',
style=('border: 1px solid #e0e0e0; background: #fff; '
'padding: 14px; color: #777;'))
if 'no commercial description' not in description.text.lower():
# strip ads
[s.extract() for s in description('small')]
self.description = ' '.join([s for s in description.strings
]).strip()
# get name
self.name = soup_rows[0].find_all('td')[1].h1.text.strip()
self._has_fetched = True
return self
def _populate(self):
if not self.id:
self.id = self.url.split('/')[-2]
data = [
{"operationName":"beer",
"variables":{"beerId":self.id},
"query":"query beer($beerId: ID!) { \n info: beer(id: $beerId) { \n id \n name \n description \n style { \n id \n name \n glasses { \n id \n name \n __typename \n } \n __typename \n } \n styleScore \n overallScore \n averageRating \n abv \n ibu \n calories \n brewer { \n id \n name \n __typename \n } \n ratingCount \n isRetired \n isUnrateable \n seasonal \n labels \n availability { \n bottle \n tap \n distribution \n __typename \n } \n __typename \n } \n} \n"},
# {"operationName":"beerReviews",
# "variables":
# {"beerId":self.id,
# "order":"RECENT",
# "first":10
# },
# "query":"query beerReviews($beerId: ID!, $authorId: ID, $order: ReviewOrder, $after: ID) { \n beerReviewsArr: beerReviews(beerId: $beerId, authorId: $authorId, order: $order, after: $after) { \n items { \n id \n comment \n score \n scores { \n appearance \n aroma \n flavor \n mouthfeel \n overall \n __typename \n } \n author { \n id \n username \n reviewCount \n __typename \n } \n checkin { \n id \n place { \n name \n city \n state { \n name \n __typename \n } \n country { \n name \n __typename \n } \n __typename \n } \n __typename \n } \n createdAt \n updatedAt \n __typename \n } \n totalCount \n last \n __typename \n } \n} \n"},
{"operationName":"beerByAlias",
"variables":{"aliasId":self.id},
"query":"query beerByAlias($aliasId: ID!) {\n beerByAlias(aliasId: $aliasId) {\n id\n name \n overallScore \n __typename \n } \n } \n"},
{"operationName":"tagDisplay",
"variables":{"beerId":self.id},
"query":"query tagDisplay($beerId: ID!, $first: Int) { \n tagDisplayArr: beerTags(beerId: $beerId, first: $first) { \n items { \n id \n urlName: plain \n __typename \n } \n __typename \n } \n} \n"
}
]
request = requests.post(
"https://beta.ratebeer.com/v1/api/graphql/"
,data=json.dumps(data)
,headers={"content-type": "application/json"}
)
try:
results = json.loads(request.text)
except:
raise rb_exceptions.JSONParseException(self.id)
beer_data = results[0]['data']['info']
if beer_data == None:
raise rb_exceptions.PageNotFound(self.id)
alias_data = results[1]['data']['beerByAlias']
if alias_data != None:
# Resolve the alias: we have all the information. We decide to just
# return the alias and not the original beer from the query.
self.name = alias_data['name']
self.id = alias_data['id']
self.url = '/beer/{0}/{1}/'.format(
self.name.replace(' ', '-').lower(),
self.id
)
return self._populate()
tag_data = results[2]['data']['tagDisplayArr']['items']
self.name = beer_data['name']
self.brewery = Brewery('/brewers/{0}/{1}/'.format(re.sub('[/ ]','-',beer_data['brewer']['name'].lower()),beer_data['brewer']['id']))
self.brewery.name = beer_data['brewer']['name']
self.brewed_at = None #no longer supported
self.overall_rating = self._format(beer_data['overallScore'])
self.style_rating = self._format(beer_data['styleScore'])
self.style = beer_data['style']['name']
self.style_url = "/beerstyles/{0}/{1}/".format(re.sub('/','-',self.style.lower()), beer_data['style']['id'])
self.img_url = "https://res.cloudinary.com/ratebeer/image/upload/w_152,h_309,c_pad,d_beer_img_default.png,f_auto/beer_{0}".format(self.id)
self.num_ratings = self._format(beer_data['ratingCount'])
self.mean_rating = self._format(beer_data['averageRating'])
self.weighted_avg = None # does not appear to exist anymore
if(beer_data['seasonal'] != 'UNKNOWN'):
self.seasonal = beer_data['seasonal']
else:
self.seasonal = None
self.ibu = self._format(beer_data['ibu'])
self.calories = self._format(beer_data['calories'])
self.abv = self._format(beer_data['abv'])
self.retired = beer_data['isRetired']
if beer_data['description']:
self.description = re.sub(r'\x92', '\'', beer_data['description'])
else:
self.description = None
if tag_data:
self.tags = [t['urlName'] for t in tag_data]
else:
self.tags = None
self._has_fetched = True
return self
def _populate(self):
if not self.id:
self.id = self.url.split("/")[-2]
data = [
{
"operationName":
"beer",
"variables": {
"beerId": self.id
},
"query":
"query beer($beerId: ID!) { \n info: beer(id: $beerId) { \n id \n name \n description \n style { \n id \n name \n glasses { \n id \n name \n __typename \n } \n __typename \n } \n styleScore \n overallScore \n averageRating \n abv \n ibu \n calories \n brewer { \n id \n name \n country \n { \n code \n name \n __typename \n } \n __typename \n } \n ratingCount \n isRetired \n isUnrateable \n seasonal \n labels \n availability { \n bottle \n tap \n distribution \n __typename \n } \n __typename \n } \n} \n",
},
# {"operationName":"beerReviews",
# "variables":
# {"beerId":self.id,
# "order":"RECENT",
# "first":10
# },
# "query":"query beerReviews($beerId: ID!, $authorId: ID, $order: ReviewOrder, $after: ID) { \n beerReviewsArr: beerReviews(beerId: $beerId, authorId: $authorId, order: $order, after: $after) { \n items { \n id \n comment \n score \n scores { \n appearance \n aroma \n flavor \n mouthfeel \n overall \n __typename \n } \n author { \n id \n username \n reviewCount \n __typename \n } \n checkin { \n id \n place { \n name \n city \n state { \n name \n __typename \n } \n country { \n name \n __typename \n } \n __typename \n } \n __typename \n } \n createdAt \n updatedAt \n __typename \n } \n totalCount \n last \n __typename \n } \n} \n"},
{
"operationName":
"beerByAlias",
"variables": {
"aliasId": self.id
},
"query":
"query beerByAlias($aliasId: ID!) {\n beerByAlias(aliasId: $aliasId) {\n id\n name \n overallScore \n __typename \n } \n } \n",
},
{
"operationName":
"tagDisplay",
"variables": {
"beerId": self.id
},
"query":
"query tagDisplay($beerId: ID!, $first: Int) { \n tagDisplayArr: beerTags(beerId: $beerId, first: $first) { \n items { \n id \n urlName: plain \n __typename \n } \n __typename \n } \n} \n",
},
]
request = requests.post(
"https://beta.ratebeer.com/v1/api/graphql/",
data=json.dumps(data),
headers={"content-type": "application/json"},
)
try:
results = json.loads(request.text)
except:
raise rb_exceptions.JSONParseException(self.id)
beer_data = results[0]["data"]["info"]
if beer_data == None:
raise rb_exceptions.PageNotFound(self.id)
alias_data = results[1]["data"]["beerByAlias"]
if alias_data != None:
raise rb_exceptions.AliasedBeer(self.id, alias_data["id"])
tag_data = results[2]["data"]["tagDisplayArr"]["items"]
self.name = beer_data["name"]
# self.brewery = Brewery(
# "/brewers/{0}/{1}/".format(
# re.sub("[/ ]", "-", beer_data["brewer"]["name"].lower()),
# beer_data["brewer"]["id"],
# )
# )
brewery_country = beer_data["brewer"]["country"]["name"]
if brewery_country == "United States":
brewery_country = "USA"
self.brewery_country = brewery_country
self.brewery_name = beer_data["brewer"]["name"]
self.brewed_at = None # no longer supported
self.overall_rating = self._format(beer_data["overallScore"])
self.style_rating = self._format(beer_data["styleScore"])
self.style = beer_data["style"]["name"]
self.style_url = "/beerstyles/{0}/{1}/".format(
re.sub("/", "-", self.style.lower()), beer_data["style"]["id"])
self.img_url = "https://res.cloudinary.com/ratebeer/image/upload/w_152,h_309,c_pad,d_beer_img_default.png,f_auto/beer_{0}".format(
self.id)
self.num_ratings = self._format(beer_data["ratingCount"])
self.mean_rating = self._format(beer_data["averageRating"])
self.weighted_avg = None # does not appear to exist anymore
if beer_data["seasonal"] != "UNKNOWN":
self.seasonal = beer_data["seasonal"]
else:
self.seasonal = None
self.ibu = self._format(beer_data["ibu"])
self.calories = self._format(beer_data["calories"])
self.abv = self._format(beer_data["abv"])
self.retired = beer_data["isRetired"]
self.description = re.sub(r"\x92", "'", beer_data["description"])
if tag_data:
self.tags = [t["urlName"] for t in tag_data]
else:
self.tags = None
self._has_fetched = True
return self
