Web scraping several a href - python

I would like to scrape this page with Python: https://statusinvest.com.br/acoes/proventos/ibovespa.
With this code:
import requests
from bs4 import BeautifulSoup as bs
URL = "https://statusinvest.com.br/acoes/proventos/ibovespa"
page = 1
req = requests.get(URL+str(page))
soup = bs(req.text, 'html.parser')
container = soup.find('div', attrs={'class','list'})
dividends = container.find('a')
for dividend in dividends:
links = dividend.find_all('a')
print(links)
But it doesn't return anything.
Can someone help me please?

Edited: you can see the below updated code to access any data you mentioned in the comment, you can modify according to your needs as all the data on that page is inside data variable.
Updated Code:
import json
import requests
from bs4 import BeautifulSoup as bs
url = "https://statusinvest.com.br"
links = []
req = requests.get(f"{url}/acoes/proventos/ibovespa")
soup = bs(req.content, 'html.parser')
data = json.loads(soup.find('input', attrs={'id': 'result'})["value"])
print("Date Com Data")
for datecom in data["dateCom"]:
print(f"{datecom['code']}\t{datecom['companyName']}\t{datecom['companyNameClean']}\t{datecom['companyId']}\t{datecom['companyId']}\t{datecom['resultAbsoluteValue']}\t{datecom['dateCom']}\t{datecom['paymentDividend']}\t{datecom['earningType']}\t{datecom['dy']}\t{datecom['recentEvents']}\t{datecom['recentEvents']}\t{datecom['uRLClear']}")
print("\nDate Payment Data")
for datePayment in data["datePayment"]:
print(f"{datePayment['code']}\t{datePayment['companyName']}\t{datePayment['companyNameClean']}\t{datePayment['companyId']}\t{datePayment['companyId']}\t{datePayment['resultAbsoluteValue']}\t{datePayment['dateCom']}\t{datePayment['paymentDividend']}\t{datePayment['earningType']}\t{datePayment['dy']}\t{datePayment['recentEvents']}\t{datePayment['recentEvents']}\t{datePayment['uRLClear']}")
print("\nProvisioned Data")
for provisioned in data["provisioned"]:
print(f"{provisioned['code']}\t{provisioned['companyName']}\t{provisioned['companyNameClean']}\t{provisioned['companyId']}\t{provisioned['companyId']}\t{provisioned['resultAbsoluteValue']}\t{provisioned['dateCom']}\t{provisioned['paymentDividend']}\t{provisioned['earningType']}\t{provisioned['dy']}\t{provisioned['recentEvents']}\t{provisioned['recentEvents']}\t{provisioned['uRLClear']}")
Seeing to the source code of that website one could fetch the json directly and get your desired links follow the below code.
Code:
import json
import requests
from bs4 import BeautifulSoup as bs
url = "https://statusinvest.com.br"
links=[]
req = requests.get(f"{url}/acoes/proventos/ibovespa")
soup = bs(req.content, 'html.parser')
data = json.loads(soup.find('input', attrs={'id': 'result'})["value"])
for datecom in data["dateCom"]:
links.append(f"{url}{datecom['uRLClear']}")
for datePayment in data["datePayment"]:
links.append(f"{url}{datePayment['uRLClear']}")
for provisioned in data["provisioned"]:
links.append(f"{url}{provisioned['uRLClear']}")
print(links)
Output:
Let me know if you have any questions :)

Related

locating child element by BeautifulSoup

I am new to BeautifulSoup and I am praticing with little tasks. Here I try to get the "previous" link in this site. The html is
here
My code is
import requests, bs4
from bs4 import BeautifulSoup
url = 'https://www.xkcd.com/'
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
result = soup.find('div', id="comic")
url2 = result.find('ul', class_='comicNav').find('a', rel='prev').find('href')
But it shows NoneType.. I have read some posts about the child elements in html, and I tried some different things. But it still does not work.. Thank you for your help in advance.
Tou could use a CSS Selector instead.
import requests, bs4
from bs4 import BeautifulSoup
url = 'https://www.xkcd.com/'
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
result = soup.select('.comicNav a[rel~="prev"]')[0]
print(result)
if you want just the href change
result = soup.select('.comicNav a[rel~="prev"]')[0]["href"]
To get prev link.find ul tag and then find a tag. Try below code.
import requests, bs4
from bs4 import BeautifulSoup
url = 'https://www.xkcd.com/'
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
url2 = soup.find('ul', class_='comicNav').find('a',rel='prev')['href']
print(url2)
Output:
/2254/

How to make beautiful soup grab only what is between a set of "[:" ":]" in a web page?

Good afternoon! How do I make Beautifulsoup grab only what is between multiple sets of "[:" and ":]" So far I have got the entire page in my soup, but it does not have tags, sadly.
What it looks like so far
I have tried a couple of things so far:
soup.findAll(text="[")
keys = soup.find("span", attrs = {"class": "objectBox objectBox-string"})
import bs4 as bs
import urllib.request
source = urllib.request.urlopen("https://login.microsoftonline.com/common/discovery/keys").read()
soup = bs.BeautifulSoup(source,'lxml')
# ---------------------------------------------
# prior script that I was playing with trying to tackle this issue
import requests
import urllib.request
import time
from bs4 import BeautifulSoup
# Set URL to scrape new certs from
newcerts = "https://login.microsoftonline.com/common/discovery/keys"
# Connect to the URL
response = requests.get(newcerts)
# Parse HTML and save to BeautifulSoup Object
soup = BeautifulSoup(response.text, "html.parser")
keys = soup.find("span", attrs = {"class": "objectBox objectBox-string"})
End goal is to retrieve the public PKI keys from Azure's website at https://login.microsoftonline.com/common/discovery/keys
Not sure if this is what you meant to grab. Try the script below:
import json
import requests
url = 'https://login.microsoftonline.com/common/discovery/keys'
res = requests.get(url)
jsonobject = json.loads(res.content)
for item in jsonobject['keys']:
print(item['x5c'])

Getting search results from youtube via bs4 python

I am trying to get the first result from the youtube search query by scraping the page and open the page in the browser! This code does not work! And I am having problems finding the right class, id or selector to get the link.
I have tried to use tags but some them return none.
import webbrowser
import urllib.request
import bs4 as bs
iarg = str(input('Query: '))
url = str('https://www.youtube.com/results?search_query={}'.format(arg))
req = urllib.request.Request(url, data=None, headers={'User-Agent':'Mozilla'})
src = urllib.request.urlopen(req)
soup = bs.BeautifulSoup(src, 'html.parser')
results = []
for elem in a = soup.find_all("a"):
link = elem.get(href)
results.append(link)
webbrowser.open(results[0])
Thanks in advance!

Scraping Amazon products names

I am trying to gather the first two pages products names on Amazon based on seller name. When I request the page, it has all elements I need ,however, when I use BeautifulSoup - they are not being listed. Here is my code:
import requests
from bs4 import BeautifulSoup
headers = {'User-Agent':'Mozilla/5.0'}
res = requests.get("https://www.amazon.com/s?me=A3WE363L17WQR&marketplaceID=ATVPDKIKX0DER", headers=headers)
#print(res.text)
soup = BeautifulSoup(res.text, "html.parser")
soup.find_all("a",href=True)
The links of products are not listed. If the Amazon API gives this information, I am open to use it (please provide some examples of its usage). Thanks a lot in advance.
I have extracted product names from alt attribute. Is this as intended?
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('https://www.amazon.com/s?me=A3WE363L17WQR&marketplaceID=ATVPDKIKX0DER')
soup = bs(r.content, 'lxml')
items = [item['alt'] for item in soup.select('.a-link-normal [alt]')]
print(items)
Over two pages:
import requests
from bs4 import BeautifulSoup as bs
url = 'https://www.amazon.com/s?i=merchant-items&me=A3WE363L17WQR&page={}&marketplaceID=ATVPDKIKX0DER&qid=1553116056&ref=sr_pg_{}'
for page in range(1,3):
r = requests.get(url.format(page,page))
soup = bs(r.content, 'lxml')
items = [item['alt'] for item in soup.select('.a-link-normal [alt]')]
print(items)

Python_Web_scraping Html Table

I'm Python beginner developer, I'm still in the learning phase.
More specifically working on scraping using requests and bs4.
When tried to scrape the following link: 'http://directorybtr.az.gov/listings/FirmSearchResults.asp?Zip%20Like%20%22850%25%22'
I used the following code :
import requests
from bs4 import BeautifulSoup
url ="http://directorybtr.az.gov/listings/FirmSearchResults.asp?Zip%20Like%20%22850%25%22"
res = requests.get(url)
soup = BeautifulSoup(res.text, 'html.parser')
res.close()
results = soup.find('table')
There is no table in results although the table are present when inspecting the source page in Chrome.
Any solution or explanation please?
Thank you
Table data is inside frame, u need to go first
import requests
from lxml import html
from bs4 import BeautifulSoup
BASE_URL = "http://directorybtr.az.gov/listings/"
URL = BASE_URL + "FirmSearchResults.asp?Zip%20Like%20%22850%25%22"
#u need session because the frame use the search results data, u cant directly go to Firms.asp
session = requests.session()
response = session.get(URL)
soup = BeautifulSoup(response.text, 'lxml')
#find the first frame
frame = soup.find("frame")
#go to the frame link ( Firms.asp )
response = session.get(BASE_URL + frame.attrs['src'])
soup = BeautifulSoup(response.text, 'lxml')
table = soup.find("table")
print table
response.close()

Categories