Web scraping with BeautifulSoup <span> - python

I'm trying to print the information inside a tag.
But I have an empty print.
There is the website: https://mubi.com/it/films/25-watts/cast?type=cast
I'm trying to print all actors name.
Here is my code:
import random
import requests
from bs4 import BeautifulSoup
url ='https://mubi.com/it/films/25-watts/cast?type=cast' #vincitori
def main():
response = requests.get(url)
html = response.text
soup1 = BeautifulSoup(html, 'html.parser')
cast = soup1.find_all('span', {'class' : 'css-1marmfu e1a7pc1u9'})
for tag in cast:
print(tag)
if __name__ == '__main__':
main()
Thank you for supporting ;)

The data you see on the page is loaded from an external URL via JavaScript (so beautifulsoup doesn't see it). You can use the requests module to simulate the Ajax request:
import json
import requests
from bs4 import BeautifulSoup
url = "https://mubi.com/it/films/25-watts/cast?type=cast"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
data = json.loads(soup.select_one("#__NEXT_DATA__").contents[0])
# uncomment this to print all data:
# print(json.dumps(data, indent=4))
film = data["props"]["initialProps"]["pageProps"]["film"]
cast_url = "https://api.mubi.com/v3/films/{}/cast_members?sort=relevance&type=cast&page=1"
cast = requests.get(
cast_url.format(film["id"]),
headers={"CLIENT": "web", "Client-Country": "US"},
).json()
# print(json.dumps(cast, indent=4))
for m in cast["cast_members"]:
print("{:<30} {:<30}".format(m["name"], m["primary_type"] or "-"))
Prints:
Daniel Hendler Actor
Jorge Temponi Actor
Alfonso Tort Actor
Valentín Rivero -
Federico Veiroj Director
Valeria Mendieta -
Roberto Suárez Actor
Gonzalo Eyherabide -
Robert Moré Actor
Ignacio Mendy -

Related

How to fetch href link from a website using BeautifulSoup

I am trying to get all the article links in a given website below.
However, my code does not print anything at all although I specified the class id and the path to it.
below is my code.
import requests
from lxml import html
from bs4 import BeautifulSoup
from urllib.request import urlopen
html = urlopen("https://uynaa.wordpress.com/category/%d0%be%d1%80%d1%87%d1%83%d1%83%d0%bb%d0%b3%d1%8b%d0%bd-%d0%bd%d0%b8%d0%b9%d1%82%d0%bb%d1%8d%d0%bb/").read()
soup = BeautifulSoup(html, "lxml")
productDivs = soup.findAll('div', attrs={'class' : 'post type-post status-publish format-standard hentry category-56456384'})
for div in productDivs:
print(div.find('h2')[a]['href'])
How do I fetch all the links?
The links are loaded dynamically via JavaScript from external URL. You can use this example to print all links:
import json
import requests
from bs4 import BeautifulSoup
data = {'action': 'infinite_scroll', 'page': 1}
api_url = 'https://uynaa.wordpress.com/?infinity=scrolling'
page = 1
while True:
data['page'] = page
data = requests.post(api_url, data=data).json()
# uncomment next line to print all data:
# print(json.dumps(data, indent=4))
for p in data['postflair']:
print(p)
if data['lastbatch']:
break
page += 1
Prints:
https://uynaa.wordpress.com/2014/01/02/2013-in-review/
https://uynaa.wordpress.com/2013/10/07/%d0%b0%d1%84%d0%b3%d0%b0%d0%bd%d0%b8%d1%81%d1%82%d0%b0%d0%bd-%d0%b0%d0%bd%d1%85%d0%b4%d0%b0%d0%b3%d1%87-%d1%88%d0%b0%d0%bb%d1%82%d0%b3%d0%b0%d0%b0%d0%bd/
https://uynaa.wordpress.com/2013/10/07/%d0%b5-%d0%ba%d0%b0%d1%81%d0%bf%d0%b5%d1%80%d1%81%d0%ba%d0%b8%d0%b9-%d0%b1%d0%b8-%d0%b4%d0%b0%d1%80%d0%b0%d0%bd%d0%b3%d1%83%d0%b9%d0%bb%d0%b0%d0%bb-%d1%82%d0%be%d0%b3%d1%82%d0%be%d0%be-%d0%b3%d1%8d/
https://uynaa.wordpress.com/2013/10/07/%d1%88%d0%b0%d0%bd%d1%85%d0%b0%d0%b9-%d0%bd%d0%be%d0%b3%d0%be%d0%be%d0%bd/
https://uynaa.wordpress.com/2013/10/07/%d1%8d%d0%bd%d1%8d-%d0%b3%d0%b0%d0%b7%d0%b0%d1%80-%d0%bc%d0%b0%d0%bd%d0%b0%d0%b9%d1%85-%d0%b1%d0%b0%d0%b9%d1%81%d0%b0%d0%bd-%d1%8e%d0%bc/
https://uynaa.wordpress.com/2013/10/07/500-%d0%b6%d0%b8%d0%bb-%d0%b0%d1%80%d1%87%d0%bb%d1%83%d1%83%d0%bb%d0%b0%d0%b0%d0%b3%d2%af%d0%b9-%d0%b4%d1%8d%d0%bb%d1%85%d0%b8%d0%b9%d0%bd-%d1%86%d0%be%d1%80%d1%8b%d0%bd-%d0%b3%d0%b0%d0%bd%d1%86/
https://uynaa.wordpress.com/2013/02/01/%d1%83%d0%bb%d0%b7-%d0%bd%d1%83%d1%82%d0%b3%d0%b8%d0%b9%d0%bd-%d0%bf%d0%b8%d1%84%d0%b0%d0%b3%d0%be%d1%80/
https://uynaa.wordpress.com/2013/01/21/%d1%82%d0%b5%d0%bb%d0%b5%d0%b2%d0%b8%d0%b7%d0%b8%d0%b9%d0%bd-%d1%82%d2%af%d2%af%d1%85%d1%8d%d0%bd-%d0%b4%d1%8d%d1%85-%d1%85%d0%b0%d0%bc%d0%b3%d0%b8%d0%b9%d0%bd-%d0%b3%d0%b0%d0%b6%d0%b8%d0%b3-%d1%88/
https://uynaa.wordpress.com/2013/01/18/%d0%b0%d0%bf%d0%be%d1%84%d0%b8%d1%81-%d0%be%d0%be%d1%81-%d2%af%d2%af%d0%b4%d1%8d%d0%bd-%d3%a9%d1%80%d0%bd%d3%a9%d1%85-%d0%b6%d2%af%d0%b6%d0%b8%d0%b3/
https://uynaa.wordpress.com/2013/01/17/%d0%b0%d1%80%d0%b8%d1%83%d0%bd%d1%82%d0%bd%d1%8b-%d0%bd%d1%83%d1%82%d0%b0%d0%b3-%d0%b8%d0%b9%d0%b3-%d1%8d%d0%b7%d1%8d%d0%b3%d0%bd%d1%8d%d1%85-%d1%85%d0%b0%d0%bd/
https://uynaa.wordpress.com/2013/01/15/%d1%81%d0%b0%d1%83%d0%b4%d1%8b%d0%bd-%d1%82%d0%b0%d0%b3%d0%bd%d1%83%d1%83%d0%bb%d1%87%d0%b8%d0%b4-%d0%b0%d1%81%d0%b0%d0%b4%d1%8b%d0%b3-%d0%be%d0%bb%d0%b6%d1%8d%d1%8d/
https://uynaa.wordpress.com/2013/01/15/%d0%bc%d0%b0%d0%bb%d0%b8%d0%b3%d1%8d%d1%8d%d1%81-%d1%81%d0%be%d0%bc%d0%b0%d0%bb%d0%b8-%d1%85%d2%af%d1%80%d1%82%d1%8d%d0%bb/
https://uynaa.wordpress.com/2013/01/10/%d1%85%d0%be%d1%80%d0%b2%d0%be%d0%be-%d0%b5%d1%80%d1%82%d3%a9%d0%bd%d1%86-%d1%85%d0%b0%d0%bb%d0%b0%d0%b0%d1%81%d0%b0%d0%bd%d0%b4-%d0%b1%d0%b0%d0%b3%d1%82%d0%b0%d0%bd%d0%b0/
https://uynaa.wordpress.com/2013/01/10/%d1%82%d0%b0%d0%bd%d0%b3%d0%b0%d1%80%d0%b0%d0%b3-%d3%a9%d1%80%d0%b3%d3%a9%d1%85-%d1%91%d1%81%d0%bb%d0%be%d0%bb-%d1%85%d2%af%d0%bb%d1%8d%d1%8d%d0%b6-%d0%b1%d0%b0%d0%b9%d0%b3-%d1%8d%d1%8d/
https://uynaa.wordpress.com/2013/01/09/%d0%b1%d0%be%d0%bb%d0%bb%d0%b8%d0%b2%d1%83%d0%b4%d1%8b%d0%bd-%d0%ba%d0%b8%d0%bd%d0%be%d0%bd%d0%be%d0%be%d1%81-%d1%87-%d0%b0%d0%b9%d0%bc%d0%b0%d0%b0%d1%80/
https://uynaa.wordpress.com/2013/01/08/%d0%bf%d0%b5%d0%bd%d1%82%d0%b0%d0%b3%d0%be%d0%bd-%d0%b1%d0%be%d0%bb%d0%be%d0%bd-%d1%82%d1%82%d0%b3-%d1%8b%d0%b3-%d1%83%d0%b4%d0%b8%d1%80%d0%b4%d0%b0%d1%85-%d0%bc%d0%b0%d0%b3%d0%b0%d0%b4%d0%bb%d0%b0/
https://uynaa.wordpress.com/2013/01/07/%d0%b7%d0%b8%d0%b0%d0%b4-%d1%82%d0%b0%d0%ba%d0%b8%d0%b5%d0%b4%d0%b4%d0%b8%d0%bd/
...and so on.
EDIT: To filter the links only to specified category, you can use this script:
import json
import requests
from bs4 import BeautifulSoup
data = {'action': 'infinite_scroll', 'page': 1}
api_url = 'https://uynaa.wordpress.com/?infinity=scrolling'
all_links = []
page = 1
while True:
data['page'] = page
data = requests.post(api_url, data=data).json()
# uncomment next line to print all data:
# print(json.dumps(data, indent=4))
soup = BeautifulSoup(data['html'], 'html.parser')
for p in soup.select('.post'):
if any('%d0%be%d1%80%d1%87%d1%83%d1%83%d0%bb%d0%b3%d1%8b%d0%bd-%d0%bd%d0%b8%d0%b9%d1%82%d0%bb%d1%8d%d0%bb' in cat['href'] for cat in p.select('[rel="category tag"]')):
if p.h2.a['href'] not in all_links:
print(p.h2.a['href'])
all_links.append(p.h2.a['href'])
if data['lastbatch']:
break
page += 1
print(len(all_links))
Prints 135 links:
...
https://uynaa.wordpress.com/2011/05/13/%e2%80%9c%d1%83%d1%85%d0%b0%d0%b0%d0%bd-%d0%bc%d1%83%d1%83%d1%82%d0%bd%d1%83%d1%83%d0%b4%d1%8b%d0%bd-%d2%af%d0%b5%e2%80%9d/
https://uynaa.wordpress.com/2011/05/04/%d2%af%d1%85%d0%bb%d0%b8%d0%b9%d0%bd-%d1%82%d0%be%d0%b3%d0%bb%d0%be%d0%be%d0%bc/
https://uynaa.wordpress.com/2011/05/04/%d0%be%d1%81%d0%b0%d0%bc%d0%b0-%d0%b1%d0%b8%d0%bd-%d0%bb%d0%b0%d0%b4%d0%b5%d0%bd%d0%b8%d0%b9%d0%b3-%d1%8f%d0%b0%d0%b6-%d0%b8%d0%bb%d1%80%d2%af%d2%af%d0%bb%d1%81%d1%8d%d0%bd-%d0%b1%d1%8d/
135
Not sure why your codes don't work. For me, I used the below codes to get all the links first.
list_href = []
a_tags = soup.find_all('a')
for tag in a_tags:
list_href.append(tag.get('href'))
The links of the articles are in list_href[5:26].

BeautifulSoup: Reading Span Class Elements

I am having some issues web scraping information from a particular pages span class element, using the beautifulsoup and requests addon in python. It keeps returning me blank information: " ". Heres my code:
headers = {'User-Agent':'Mozilla/5.0'}
res = requests.get('https://www.theweathernetwork.com/ca/weather/ontario/toronto')
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, 'html.parser')
weather_elem = soup.find('span', {'class':'wxcondition'})
weather = weather_elem
print(weather)
return weather`
The data is loaded through JavaScript so BeautifulSoup doesn't see anything. But you can simulate the Ajax with the requests module:
import json
import requests
from bs4 import BeautifulSoup
url = 'https://www.theweathernetwork.com/ca/weather/ontario/toronto'
soup = BeautifulSoup(requests.get(url).content, 'html.parser')
place_code = soup.select_one('link[rel="alternate"]')['href'].split('=')[-1].lower()
ajax_url = 'https://weatherapi.pelmorex.com/api/v1/observation/placecode/' + place_code
data = requests.get(ajax_url).json()
# uncomment to print all data:
# print(json.dumps(data, indent=4))
print(data['observation']['weatherCode']['text'])
Prints:
Partly cloudy

data scraping - field value - issue

I like to obtain actual informaction about the numbers of infected from this website: https://www.gov.pl/web/koronawirus/wykaz-zarazen-koronawirusem-sars-cov-2
my code looks like:
import requests
from bs4 import BeautifulSoup
adresURL = 'https://www.gov.pl/web/koronawirus/wykaz-zarazen-koronawirusem-sars-cov-2'
res = requests.get(adresURL)
soup = BeautifulSoup(res.text, 'html.parser')
data = soup.select('.details-property-value')
print(data)
as a result I'm receiving:
[<div class="details-property-value" tabindex="0">{{selectedRecord[commonColumns[index]] || '-'}}</div>]
Any ideas how to get value of fields ? Am i missing sth ?
I'm guessing you're trying to scrape the table on that page. It looks like there is some JSON baked into the HTML:
import requests
from bs4 import BeautifulSoup
import json
url = "https://www.gov.pl/web/koronawirus/wykaz-zarazen-koronawirusem-sars-cov-2"
response = requests.get(url)
response.raise_for_status()
soup = BeautifulSoup(response.content, "html.parser")
data = json.loads(soup.find("pre", {"id": "registerData"}).text)
print(data)

BS4 + html, b Tag issue

This question is about web scraping with bs4
this is the code I have written:
import requests
from bs4 import BeautifulSoup
import json
import csv
page = requests.get('https://www.alibaba.com/product-detail/Portable-Small-USB-Travel-LED-Makeup_60830030133.html?spm=a2700.details.maylikever.2.1fb53cc2uSVPvx')
# Create a BeautifulSoup object
soup = BeautifulSoup(page.text, 'html.parser')
#extract product score **(This is what I want to extract)**
stars = soup.select_one('a[class="score-lite"]', namespaces=None, flags=0)
#score = json.loads(stars)
print('Stars', stars)
My outcome:
<a class="score-lite" data-spm-click="gostr=/details.index.reviewLevel;locaid=dreviewLevel" href="https://onuliss.en.alibaba.com/company_profile/feedback.html" target="_blank"><b>4.8 </b><img src="//img.alicdn.com/tfs/TB1MJPmiQL0gK0jSZFtXXXQCXXa-8-9.svg"/></a>
The outcome I want is just the 4.8 number between the 'b' tags
What do I have to do with the = soup.select_one() function?
Thank you very much :)
Try with a more specific selector, the string property of the match and strip() to get rid of eventual extra spaces.
import requests
from bs4 import BeautifulSoup
import json
import csv
page = requests.get('https://www.alibaba.com/product-detail/Portable-Small-USB-Travel-LED-Makeup_60830030133.html?spm=a2700.details.maylikever.2.1fb53cc2uSVPvx')
# Create a BeautifulSoup object
soup = BeautifulSoup(page.text, 'html.parser')
#extract product score **(This is what I want to extract)**
stars = soup.select_one('a[class="score-lite"] > b', namespaces=None, flags=0).get_text(strip=True)
#score = json.loads(stars)
print('Stars', stars)
Stars 4.8
how about SimplifiedDoc
import requests
from simplified_scrapy.simplified_doc import SimplifiedDoc
page = requests.get('https://www.alibaba.com/product-detail/Portable-Small-USB-Travel-LED-Makeup_60830030133.html?spm=a2700.details.maylikever.2.1fb53cc2uSVPvx')
# Create a SimplifiedDoc object
doc = SimplifiedDoc(page.text)
# get element use tag and class
stars = doc.getElement('a','class',"score-lite")
print('Stars', stars.text, stars.b.text) # Stars 4.8 4.8
import requests
from bs4 import BeautifulSoup
r = requests.get(
'https://www.alibaba.com/product-detail/Portable-Small-USB-Travel-LED-Makeup_60830030133.html?spm=a2700.details.maylikever.2.1fb53cc2uSVPvx')
soup = BeautifulSoup(r.text, 'html.parser')
if r.status_code == 200:
item = soup.find('a', {'class': 'score-lite'}).find('b')
print(item.get_text(strip=True))
output:
4.8

Scraping links from buttons on a page

I am trying to scrape the links from the "box score" button on this page. The button is supposed to look like this
http://www.espn.com/nfl/boxscore?gameId=400874795
I tried to use this code to see if I could access the buttons but I cannot.
from bs4 import BeautifulSoup
import requests
url = 'http://www.espn.com/nfl/scoreboard/_/year/2016/seasontype/1/week/2'
advanced = url
r = requests.get(advanced)
data = r.text
soup = BeautifulSoup(data,"html.parser")
for link in soup.find_all('a'):
print link
As wpercy mentions in his comment, you can't do this using requests, as a suggestion you should use selenium together with Chromedriver/PhantomJS for handling the JavaScript:
from selenium import webdriver
from bs4 import BeautifulSoup
url = "http://www.espn.com/nfl/scoreboard/_/year/2016/seasontype/1/week/2"
browser = webdriver.Chrome()
browser.get(url)
html = browser.page_source
soup = BeautifulSoup(html,'html.parser')
boxList = soup.findAll('a',{'name':'&lpos=nfl:scoreboard:boxscore'})
All score buttons's a tag have the attribute name = &lpos=nfl:scoreboard:boxscore, so we first use .findAll and now a simple list comprehension can extract each href attribute:
>>> links = [box['href'] for box in boxList]
>>> links
['/nfl/boxscore?gameId=400874795', '/nfl/boxscore?gameId=400874854', '/nfl/boxscore?gameId=400874753', '/nfl/boxscore?gameId=400874757', '/nfl/boxscore?gameId=400874772', '/nfl/boxscore?gameId=400874777', '/nfl/boxscore?gameId=400874767', '/nfl/boxscore?gameId=400874812', '/nfl/boxscore?gameId=400874761', '/nfl/boxscore?gameId=400874764', '/nfl/boxscore?gameId=400874781', '/nfl/boxscore?gameId=400874796', '/nfl/boxscore?gameId=400874750', '/nfl/boxscore?gameId=400873867', '/nfl/boxscore?gameId=400874775', '/nfl/boxscore?gameId=400874798']
here is the solution i did , and it scrapes all the link which are there on the url you have provided in your answer . you can check it out
# from BeautifulSoup import *
from bs4 import BeautifulSoup
# import requests
import urllib
url = 'http://www.espn.com/nfl/scoreboard/_/year/2016/seasontype/1/week/2'
# advanced = url
html = urllib.urlopen(url).read()
# r = requests.get(html)
# data = r.text
soup = BeautifulSoup(html)
tags = soup('a')
# for link in soup.find_all('a'):
for i,tag in enumerate(tags):
# print tag;
print i;
ans = tag.get('href',None)
print ans;
print "\n";
The answer from Gopal Chitalia didn't work for me, so I decided to post the working one (for python 3.6.5)
# from BeautifulSoup import *
from bs4 import BeautifulSoup
# import requests
import urllib
url = 'http://www.espn.com/nfl/scoreboard/_/year/2016/seasontype/1/week/2'
# advanced = url
html = urllib.request.urlopen(url)
# urlopen(url).read()
# r = requests.get(html)
# data = r.text
soup = BeautifulSoup(html)
tags = soup('a')
# for link in soup.find_all('a'):
for i,tag in enumerate(tags):
# print tag;
print (i);
ans = tag.get('href',None)
print (ans);
print ("\n");

Categories