Web Scraping with Python - blank return - python

I'm trying to scrape reviews from TrustPilot, but the code always return with blank sheets and the headers/categories I specified. Could someone help me with this?
from bs4 import BeautifulSoup, SoupStrainer
import pandas as pd
driver= webdriver.Chrome()
names=[] #List to store name of the product
headers=[] #List to store price of the product
bodies=[]
ratings=[] #List to store rating of the product
dates=[]
#driver = webdriver.Chrome(ChromeDriverManager().install())
driver.get("https://www.trustpilot.com/review/birchbox.com?page=2")
content = driver.page_source
soup = BeautifulSoup(content, "html.parser", parse_only=SoupStrainer('a'))
for a in soup.findAll('a', href=True, attrs={'class':'reviews-container'}):
name=a.find('div', attrs={'class':'consumer-information_name'})
header=a.find('div', attrs={'class':'review-content_title'})
body=a.find('div', attrs={'class':'review-content_text'})
rating=a.find('div', attrs={'class':'star-rating star-rating--medium'})
date=a.find('div', attrs={'class':'review-date--tooltip-target'})
names.append(name.text)
headers.append(header.text)
bodies.append(body.text)
ratings.append(rating.text)
dates.append(date.text)
print ('webpage, no errors')
df = pd.DataFrame({'User Name':names,'Header':headers,'Body':bodies,'Rating':ratings,'Date':dates})
df.to_csv('reviews02.csv', index=False, encoding='utf-8')
print ('csv made')```

The issue is soup.findAll('a', href=True, attrs={'class':'reviews-container'}) is not finding any results, so there are 0 iterations in the loop. Make sure you are using the correct tags and class names. Also you don't need to use a loop because BeautifulSoup has a find_all method. I used the requests module to open the web page, though it shouldn't make a difference.
from bs4 import BeautifulSoup
import requests
req = requests.get("https://www.trustpilot.com/review/birchbox.com?page=2")
content = req.content
soup = BeautifulSoup(content, "lxml")
names = soup.find_all('div', attrs={'class': 'consumer-information__name'})
headers = soup.find_all('h2', attrs={'class':'review-content__title'})
bodies = soup.find_all('p', attrs={'class':'review-content__text'})
ratings = soup.find_all('div', attrs={'class':'star-rating star-rating--medium'})
dates = soup.find_all('div', attrs={'class':'review-content-header__dates'})
And now each list has 20 entries.

Related

Pulling p tags from multiple URLs

I've struggled on this for days and not sure what the issue could be - basically, I'm trying to extract the profile box data (picture below) of each link -- going through inspector, I thought I could pull the p tags and do so.
I'm new to this and trying to understand, but here's what I have thus far:
-- a code that (somewhat) succesfully pulls the info for ONE link:
import requests
from bs4 import BeautifulSoup
# getting html
url = 'https://basketball.realgm.com/player/Darius-Adams/Summary/28720'
req = requests.get(url)
soup = BeautifulSoup(req.text, 'html.parser')
container = soup.find('div', attrs={'class', 'main-container'})
playerinfo = container.find_all('p')
print(playerinfo)
I then also have a code that pulls all of the HREF tags from multiple links:
from bs4 import BeautifulSoup
import requests
def get_links(url):
links = []
website = requests.get(url)
website_text = website.text
soup = BeautifulSoup(website_text)
for link in soup.find_all('a'):
links.append(link.get('href'))
for link in links:
print(link)
print(len(links))
get_links('https://basketball.realgm.com/dleague/players/2022')
get_links('https://basketball.realgm.com/dleague/players/2021')
get_links('https://basketball.realgm.com/dleague/players/2020')
So basically, my goal is to combine these two, and get one code that will pull all of the P tags from multiple URLs. I've been trying to do it, and I'm really not sure at all why this isn't working here:
from bs4 import BeautifulSoup
import requests
def get_profile(url):
profiles = []
req = requests.get(url)
soup = BeautifulSoup(req.text, 'html.parser')
container = soup.find('div', attrs={'class', 'main-container'})
for profile in container.find_all('a'):
profiles.append(profile.get('p'))
for profile in profiles:
print(profile)
get_profile('https://basketball.realgm.com/player/Darius-Adams/Summary/28720')
get_profile('https://basketball.realgm.com/player/Marial-Shayok/Summary/26697')
Again, I'm really new to web scraping with Python but any advice would be greatly appreciated. Ultimately, my end goal is to have a tool that can scrape this data in a clean way all at once.
(Player name, Current Team, Born, Birthplace, etc).. maybe I'm doing it entirely wrong but any guidance is welcome!
You need to combine your two scripts together and make requests for each player. Try the following approach. This searches for <td> tags that have the data-td=Player attribute:
import requests
from bs4 import BeautifulSoup
def get_links(url):
data = []
req_url = requests.get(url)
soup = BeautifulSoup(req_url.content, "html.parser")
for td in soup.find_all('td', {'data-th' : 'Player'}):
a_tag = td.a
name = a_tag.text
player_url = a_tag['href']
print(f"Getting {name}")
req_player_url = requests.get(f"https://basketball.realgm.com{player_url}")
soup_player = BeautifulSoup(req_player_url.content, "html.parser")
div_profile_box = soup_player.find("div", class_="profile-box")
row = {"Name" : name, "URL" : player_url}
for p in div_profile_box.find_all("p"):
try:
key, value = p.get_text(strip=True).split(':', 1)
row[key.strip()] = value.strip()
except: # not all entries have values
pass
data.append(row)
return data
urls = [
'https://basketball.realgm.com/dleague/players/2022',
'https://basketball.realgm.com/dleague/players/2021',
'https://basketball.realgm.com/dleague/players/2020',
]
for url in urls:
print(f"Getting: {url}")
data = get_links(url)
for entry in data:
print(entry)

Beautiful Soup - HTML Parser seems to not pull in things after comment

Just started learning python (3.8), building a scraper to get some football stats. Here's the code so far.
I originally wanted to pull a div with id = 'div_alphabet' which is clearly in the html tree on the website, but for some reason bs4 wasn't pulling it in. I investigated further and noticed that when I pull in the parent div 'all_alphabet' and then look for all child divs, 'div_alphabet' is missing. The only thing weird about the html structure is the long block comment that sits right above 'div_alphabet'. Is this a potential issue?
https://www.pro-football-reference.com/players
import requests
from bs4 import BeautifulSoup
URL = 'https://www.pro-football-reference.com/'
homepage = requests.get(URL)
home_soup = BeautifulSoup(homepage.content, 'html.parser')
players_nav_URL = home_soup.find(id='header_players').a['href']
players_directory_page = requests.get(URL + players_nav_URL)
players_directory_soup = BeautifulSoup(players_directory_page.content, 'html.parser')
alphabet_nav = players_directory_soup.find(id='all_alphabet')
all_letters = alphabet_nav.find_all('div')
print(all_letters)
links = [a['href'] for a in players_directory_soup.select('ul.page_index li div a')]
names = [a.get_text() for a in players_directory_soup.select('ul.page_index li div a')]
This gives you a list and names of all the relative links of alphabetised players.
I wouldn't concern yourself with the div_alphabet it doesn't have any useful information.
Here we are selecting the ul tag with class "page_index". But you'll get a list, so we need to do a for loop and grab the href attribute. The get_text() also gives you the names.
If you haven't come across list comprehensions then this would also be acceptable.
links = []
for a in players_directory_soup.select('ul.page_index li div a'):
links.append(a['href'])
names = []
for a in players_directory_soup.select('ul.page_index li div a'):
names.append(a.get_text())
Something like this cod will make it:
import requests
from bs4 import BeautifulSoup
headers = {'User-Agent': 'Mozilla/5.0 '}
r = requests.get('https://www.pro-football-reference.com/players/', headers=headers)
soup = BeautifulSoup(r.text, 'lxml')
data = soup.select('ul.page_index li div')
for link in data:
print(*[f'{a.get("href")}\n' for a in link.select('a')])
A more useful way to do this is to make a DataFrame with pandas of it and save it as a csv or something:
import requests
from bs4 import BeautifulSoup
import pandas as pd
players = []
headers = {'User-Agent': 'Mozilla/5.0 '}
r = requests.get('https://www.pro-football-reference.com/players/', headers=headers)
soup = BeautifulSoup(r.text, 'lxml')
data = soup.select('ul.page_index li div a')
for link in data:
players.append([link.get_text(strip=True), 'https://www.pro-football-reference.com' + link.get('href')])
print(players[0])
df = pd.DataFrame(players, columns=['Player name', 'Url'])
print(df.head())
df.to_csv('players.csv', index=False)

Get a <span> value using python web scrape

I am trying to get a product price using BeautifulSoup in python.
But i keep getting erroes, no matter what I try.
The picture of the site i am trying to web scrape
I want to get the 19,90 value.
I have already done a code to get all the product names, and now need their prices.
import requests
from bs4 import BeautifulSoup
url = 'https://www.zattini.com.br/busca?nsCat=Natural&q=amaro&searchTermCapitalized=Amaro&page=1'
page = requests.get(url)
soup = BeautifulSoup(page.text, 'html.parser')
price = soup.find('span', itemprop_='price')
print(price)
Less ideal is parsing out the JSON containing the prices
import requests
import json
import pandas as pd
from bs4 import BeautifulSoup
url = 'https://www.zattini.com.br/busca?nsCat=Natural&q=amaro&searchTermCapitalized=Amaro&page=1'
page = requests.get(url)
soup = BeautifulSoup(page.content, 'lxml')
scripts = [script.text for script in soup.select('script') if 'var freedom = freedom ||' in script.text]
pricesJson = scripts[0].split('"items":')[1].split(']')[0] + ']'
prices = [item['price'] for item in json.loads(pricesJson)]
names = [name.text for name in soup.select('#item-list [itemprop=name]')]
results = list(zip(names,prices))
df = pd.DataFrame(results)
print(df)
Sample output:
span[itemprop='price'] is generated by javascript. Original value stored in div[data-final-price] with value like 1990 and you can format it to 19,90 with Regex.
import re
...
soup = BeautifulSoup(page.text, 'html.parser')
prices = soup.select('div[data-final-price]')
for price in prices:
price = re.sub(r'(\d\d$)', r',\1', price['data-final-price'])
print(price)
Results:
19,90
134,89
29,90
119,90
104,90
59,90
....

Python bs4 BeautifulSoup: findall gives empty bracket

when i run this code it gives me an empty bracket. Im new to web scraping so i dont know what im doing wrong.
import requests
from bs4 import BeautifulSoup
url = 'https://www.amazon.com/s/ref=nb_sb_noss_1?url=search-alias%3Daps&field-keywords=laptop'
r = requests.get(url)
soup = BeautifulSoup(r.text, 'html.parser')
container = soup.findAll('li', {'class': 's-result-item celwidget '})
#btw the space is also there in the html code
print(container)
results:
[]
What i tried is to grab the html code from the site, and to soup trough the li tags where all the information is stored so I can print out all the information in a for loop.
Also if someone wants to explain how to use BeautifulSoup we can always talk.
Thank you guys.
So a working code that grabs product and price would could look something like this.
import requests
from bs4 import BeautifulSoup
url = 'https://www.amazon.com/s/ref=nb_sb_noss_1?url=search-alias%3Daps&field-keywords=laptop'
r = requests.get(url, headers={'User-Agent': 'Mozilla Firefox'})
soup = BeautifulSoup(r.text, 'html.parser')
container = soup.findAll('li', {'class': 's-result-item celwidget '})
for cont in container:
h2 = cont.h2.text.strip()
# Amazon lists prices in two ways. If one fails, use the other
try:
currency = cont.find('sup', {'class': 'sx-price-currency'}).text.strip()
price = currency + cont.find('span', {'class': 'sx-price-whole'}).text.strip()
except:
price = cont.find('span', {'class': 'a-size-base a-color-base'})
print('Product: {}, Price: {}'.format(h2, price))
Let me know if that helps you further...

Web crawler - following links

Please bear with me. I am quite new at Python - but having a lot of fun. I am trying to code a web crawler that crawls through election results from the last referendum in Denmark. I have managed to extract all the relevant links from the main page. And now I want Python to follow each of the 92 links and gather 9 pieces of information from each of those pages. But I am so stuck. Hope you can give me a hint.
Here is my code:
import requests
import urllib2
from bs4 import BeautifulSoup
# This is the original url http://www.kmdvalg.dk/
soup = BeautifulSoup(urllib2.urlopen('http://www.kmdvalg.dk/').read())
my_list = []
all_links = soup.find_all("a")
for link in all_links:
link2 = link["href"]
my_list.append(link2)
for i in my_list[1:93]:
print i
# The output shows all the links that I would like to follow and gather information from. How do I do that?
Here is my solution using lxml. It's similar to BeautifulSoup
import lxml
from lxml import html
import requests
page = requests.get('http://www.kmdvalg.dk/main')
tree = html.fromstring(page.content)
my_list = tree.xpath('//div[#class="LetterGroup"]//a/#href') # grab all link
print 'Length of all links = ', len(my_list)
my_list is a list consist of all links. And now you can use for loop to scrape information inside each page.
We can for loop through each links. Inside each page, you can extract information as example. This is only for the top table.
table_information = []
for t in my_list:
page_detail = requests.get(t)
tree = html.fromstring(page_detail.content)
table_key = tree.xpath('//td[#class="statusHeader"]/text()')
table_value = tree.xpath('//td[#class="statusText"]/text()') + tree.xpath('//td[#class="statusText"]/a/text()')
table_information.append(zip([t]*len(table_key), table_key, table_value))
For table below the page,
table_information_below = []
for t in my_list:
page_detail = requests.get(t)
tree = html.fromstring(page_detail.content)
l1 = tree.xpath('//tr[#class="tableRowPrimary"]/td[#class="StemmerNu"]/text()')
l2 = tree.xpath('//tr[#class="tableRowSecondary"]/td[#class="StemmerNu"]/text()')
table_information_below.append([t]+l1+l2)
Hope this help!
A simple approach would be to iterate through your list of urls and parse them each individually:
for url in my_list:
soup = BeautifulSoup(urllib2.urlopen(url).read())
# then parse each page individually here
Alternatively, you could speed things up significantly using Futures.
from requests_futures.sessions import FuturesSession
def my_parse_function(html):
"""Use this function to parse each page"""
soup = BeautifulSoup(html)
all_paragraphs = soup.find_all('p')
return all_paragraphs
session = FuturesSession(max_workers=5)
futures = [session.get(url) for url in my_list]
page_results = [my_parse_function(future.result()) for future in results]
This would be my solution for your problem
import requests
from bs4 import BeautifulSoup
def spider():
url = "http://www.kmdvalg.dk/main"
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('div', {'class': 'LetterGroup'}):
anc = link.find('a')
href = anc.get('href')
print(anc.getText())
print(href)
# spider2(href) call a second function from here that is similar to this one(making url = to herf)
spider2(href)
print("\n")
def spider2(linktofollow):
url = linktofollow
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('tr', {'class': 'tableRowPrimary'}):
anc = link.find('td')
print(anc.getText())
print("\n")
spider()
its not done... i only get a simple element from the table but you get the idea and how its supposed to work.
Here is my final code that works smooth. Please let me know if I could have done it smarter!
import urllib2
from bs4 import BeautifulSoup
import codecs
f = codecs.open("eu2015valg.txt", "w", encoding="iso-8859-1")
soup = BeautifulSoup(urllib2.urlopen('http://www.kmdvalg.dk/').read())
liste = []
alle_links = soup.find_all("a")
for link in alle_links:
link2 = link["href"]
liste.append(link2)
for url in liste[1:93]:
soup = BeautifulSoup(urllib2.urlopen(url).read().decode('iso-8859-1'))
tds = soup.findAll('td')
stemmernu = soup.findAll('td', class_='StemmerNu')
print >> f, tds[5].string,";",tds[12].string,";",tds[14].string,";",tds[16].string,";", stemmernu[0].string,";",stemmernu[1].string,";",stemmernu[2].string,";",stemmernu[3].string,";",stemmernu[6].string,";",stemmernu[8].string,";",'\r\n'
f.close()

Categories