Парсинг данных с Vivino.com ⇐ Python
-
Anonymous
Парсинг данных с Vivino.com
I am trying to collect data from vivino.com and the DataFrame comes out empty, I can see that my soup is collecting the website info, but can't see where my error is.
My code:
def get_data(): headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0", "Accept-Encoding":"gzip, deflate", "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "DNT":"1","Connection":"close", "Upgrade-Insecure-Requests":"1"} r = requests.get("https://www.vivino.com/explore?e=eJzLLb ... mCEgC1YxlZ", headers=headers)#, proxies=proxies) content = r.content soup = BeautifulSoup(content, "html.parser") and as I need the wine maker, wine name and ratings this is how I've tried this:
alls = [] for d in soup.findAll('div', attrs={'class':'explorerCard__titleColumn--28kWX'}): Winery = d.find_all("a", attrs={"class":"VintageTitle_winery--2YoIr"}) Wine = d.find_all("a", attrs={"class":"VintageTitle_wine--U7t9G"}) Rating = d.find_all("div", attrs={"class":"VivinoRatingWide_averageValue--1zL_5"}) num_Reviews = d.find_all("div", attrs={"class":"VivinoRatingWide__basedOn--s6y0t"}) Stars = d.find_all("div", attrs={"aria-label":"rating__rating--ZZb_x rating__vivino--1vGCy"}) alll=[] if Winery is not None: #print(n[0]["alt"]) alll.append(Winery.text) else: alll.append("unknown-winery") if Wine is not None: #print(wine.text) alll.append(wine.text) else: alll.append("0") if Rating is not None: #print(rating.text) alll.append(rating.text) else: alll.append("0") ... and then getting the data into a DataFrame:
results = [] for i in range(1, no_pages+1): results.append(get_data()) flatten = lambda l: [item for sublist in l for item in sublist] df = pd.DataFrame(flatten(results),columns=['Winery','Wine','Rating','num_review', 'Stars']) df.to_csv('redwines.csv', index=False, encoding='utf-8')
Источник: https://stackoverflow.com/questions/622 ... vivino-com
I am trying to collect data from vivino.com and the DataFrame comes out empty, I can see that my soup is collecting the website info, but can't see where my error is.
My code:
def get_data(): headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0", "Accept-Encoding":"gzip, deflate", "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "DNT":"1","Connection":"close", "Upgrade-Insecure-Requests":"1"} r = requests.get("https://www.vivino.com/explore?e=eJzLLb ... mCEgC1YxlZ", headers=headers)#, proxies=proxies) content = r.content soup = BeautifulSoup(content, "html.parser") and as I need the wine maker, wine name and ratings this is how I've tried this:
alls = [] for d in soup.findAll('div', attrs={'class':'explorerCard__titleColumn--28kWX'}): Winery = d.find_all("a", attrs={"class":"VintageTitle_winery--2YoIr"}) Wine = d.find_all("a", attrs={"class":"VintageTitle_wine--U7t9G"}) Rating = d.find_all("div", attrs={"class":"VivinoRatingWide_averageValue--1zL_5"}) num_Reviews = d.find_all("div", attrs={"class":"VivinoRatingWide__basedOn--s6y0t"}) Stars = d.find_all("div", attrs={"aria-label":"rating__rating--ZZb_x rating__vivino--1vGCy"}) alll=[] if Winery is not None: #print(n[0]["alt"]) alll.append(Winery.text) else: alll.append("unknown-winery") if Wine is not None: #print(wine.text) alll.append(wine.text) else: alll.append("0") if Rating is not None: #print(rating.text) alll.append(rating.text) else: alll.append("0") ... and then getting the data into a DataFrame:
results = [] for i in range(1, no_pages+1): results.append(get_data()) flatten = lambda l: [item for sublist in l for item in sublist] df = pd.DataFrame(flatten(results),columns=['Winery','Wine','Rating','num_review', 'Stars']) df.to_csv('redwines.csv', index=False, encoding='utf-8')
Источник: https://stackoverflow.com/questions/622 ... vivino-com
