Develop Reference

How to get the value of a "hidden" href?

I'm working with web scraping to, at first, collect the total pages. I have tested the code I made for another site and however I am having a problem getting the next page link (href).
Here's the code:
from urllib.parse import urljoin
from bs4 import BeautifulSoup
import requests
userName = 'brendanm1975' # just for testing
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}
pages = []
with requests.Session() as session:
page_number = 1
url = "https://www.last.fm/user/"+userName+"/library/artists?page="
while True:
response = session.get(url, headers=headers)
soup = BeautifulSoup(response.content, 'html.parser')
pages.append(url)
next_link = soup.find("li", class_="pagination-next")
if next_link is None:
break
url = urljoin(url, next_link["href"])
page_number += 1
As you can see, the href of this site presents the link as "?page=2", which does not allow me to get its content (https://www.last.fm/user/brendanm1975/library/artists?page=2).
I've already inspected the variables, and I'm getting the values.
print(url) # output: https://www.last.fm/user/brendanm1975/library/artists?page=
next_link.find('a').get('href') # output: '?page=2'
Does anyone know how to get around this?

What happens?
You try to urljoin(url, next_link["href"]) but next_link do not have an attribute href cause you are selecting the <li> not the <a>.
How to fix?
Option#1 - Just select the <a> in your urljoin():
url = urljoin(url, next_link.a["href"])
Option#2 - Select the <a> directly:
next_link = soup.select_one('li.pagination-next a')
Example
from urllib.parse import urljoin
from bs4 import BeautifulSoup
import requests
userName = 'brendanm1975' # just for testing
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}
pages = []
with requests.Session() as session:
url = "https://www.last.fm/user/"+userName+"/library/artists?page=1"
while True:
response = session.get(url, headers=headers)
soup = BeautifulSoup(response.content, 'html.parser')
pages.append(url)
next_link = soup.find("li", class_="pagination-next")
if next_link is None:
break
url = urljoin(url, next_link.a["href"])
Output
['https://www.last.fm/user/brendanm1975/library/artists?page=1',
'https://www.last.fm/user/brendanm1975/library/artists?page=2',
'https://www.last.fm/user/brendanm1975/library/artists?page=3',
'https://www.last.fm/user/brendanm1975/library/artists?page=4',
'https://www.last.fm/user/brendanm1975/library/artists?page=5',
'https://www.last.fm/user/brendanm1975/library/artists?page=6',
'https://www.last.fm/user/brendanm1975/library/artists?page=7',
'https://www.last.fm/user/brendanm1975/library/artists?page=8',
'https://www.last.fm/user/brendanm1975/library/artists?page=9',
'https://www.last.fm/user/brendanm1975/library/artists?page=10',
'https://www.last.fm/user/brendanm1975/library/artists?page=11',
'https://www.last.fm/user/brendanm1975/library/artists?page=12',
'https://www.last.fm/user/brendanm1975/library/artists?page=13',
'https://www.last.fm/user/brendanm1975/library/artists?page=14',
'https://www.last.fm/user/brendanm1975/library/artists?page=15',
'https://www.last.fm/user/brendanm1975/library/artists?page=16',
'https://www.last.fm/user/brendanm1975/library/artists?page=17',
'https://www.last.fm/user/brendanm1975/library/artists?page=18',...]

Getting a specific value

hey i want to get the last href value in the navigation bar which is this part "/cat/cremes-solaires-indice-30" but i got error that the string index out of range thank you for helping me :)
from bs4 import BeautifulSoup as soup
PAGE_URL = https://www.e.leclerc/fp/sunissime-bb-fluide-protecteur-anti-age-global-spf30-40ml-3508240006457
def product():
response = requests.get(PAGE_URL, headers=HEADERS)
soupe = soup(response.content, 'html5lib')
sauce = soupe.find_all("div", class_="product-breadcrumb")
for x in sauce:
a = x.select('[href]')
print(type(a))
for i in a:
u = i.get("href")
print(u[-2])```

You can find main p tag and from it use find_all method on a tag where it returns list of tag from it extract href
from bs4 import BeautifulSoup
import requests
headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36"}
req = requests.get('https://www.e.leclerc/fp/sunissime-bb-fluide-protecteur-anti-age-global-spf30-40ml-3508240006457',headers=headers)
soup = BeautifulSoup(req.text, 'html.parser')
soup.find("p",class_="wrapper d-inline-block").find_all("a")[-1]['href']
Output:
'/cat/cremes-solaires-indice-30'

The object 'u' is not a dictionary or any other data set storing object , So every time the loop repeats the variable u is being over written . So you can either declare a list or can make the variable global .
Method 1:
from bs4 import BeautifulSoup as soup
PAGE_URL = https://www.e.leclerc/fp/sunissime-bb-fluide-protecteur-anti-age-global-spf30-40ml-3508240006457
def product():
response = requests.get(PAGE_URL, headers=HEADERS)
soupe = soup(response.content, 'html5lib')
sauce = soupe.find_all("div", class_="product-breadcrumb")
for x in sauce:
a = x.select('[href]')
print(type(a))
for i in a:
global u
u = i.get("href")
print(u)
Method 2:
from bs4 import BeautifulSoup as soup
PAGE_URL = https://www.e.leclerc/fp/sunissime-bb-fluide-protecteur-anti-age-global-spf30-40ml-3508240006457
def product():
response = requests.get(PAGE_URL, headers=HEADERS)
soupe = soup(response.content, 'html5lib')
sauce = soupe.find_all("div", class_="product-breadcrumb")
for x in sauce:
a = x.select('[href]')
u = []
print(type(a))
for i in a:
u.append(i.get("href"))
print(u[-1])
P.S : Your code is missing many thing else

python requests module find urls within the urls already found

This script returns a list of URLs found on the web page.
import requests
from bs4 import BeautifulSoup as BS
from bs4 import Comment
with requests.session() as r:
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0'}
r = requests.get('https://ctflearn.com', verify=False, headers=headers)
response = r.text
soup = BS(response, 'html.parser')
tags = soup.find_all('a')
for tag in tags:
links = tag.get('href')
if links[0] == '/':
appended_link = 'https://ctflearn.com' + links
print(appended_link)
elif links[0] == '#':
pass
else:
print(links)
However, what I am interested in is to visit these web pages and find the links within these pages as well. I know it is possible by using a for loop, but I don't know how to implement it.
Thanks for the help.

You could simply try to use two lists (to_visit and visited) with a check if a url is already in one of those lists before you add it to to_visit.
import requests
from bs4 import BeautifulSoup as BS
from bs4 import Comment
with requests.session() as r:
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0'}
to_visit = ['https://ctflearn.com']
visited = []
while (len(to_visit) > 0):
url = to_visit.pop(0)
visited.append(url)
print('visited: "{0}"'.format(url))
r = requests.get(url, verify=True, headers=headers)
response = r.text
soup = BS(response, 'html.parser')
tags = soup.find_all('a')
for tag in tags:
links = tag.get('href')
if links == None:
continue
elif links[0] == '/':
appended_link = 'https://ctflearn.com' + links
if (appended_link not in visited and appended_link not in to_visit):
to_visit.append(appended_link)
elif links[0] == '#':
pass
else:
if (links not in visited and links not in to_visit):
to_visit.append(links)
but at some point you will run into a problem because you will find and try to access something that is not an url which is why I would recommend using a validator:
import validators
validators.url(url) # returns True if "url" is a valid url

Python BeautifulSoup4 not nesting/iterating

I'm trying to scrape product data of off adidas and nike and am successful in getting the first product's details, but can't get it to iterate through to any additional products. It looks like this is because bs4 is not nesting items inside the I'm pointing to into a list and therefore not allowing me to iterate. I've tried searching around for solutions, but most things I read just point to changing the parser to lxml or html5. I don't think its an issue with the site's html since I'm getting the same issue for both nike and adidas. Both chunks of code are:
Nike
from bs4 import BeautifulSoup
import requests
import pandas as pd
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0'}
url = 'https://www.nike.com/w/mens-shoes-nik1zy7ok'
page = requests.get(url, headers=headers)
if page.status_code == 200:
soup = BeautifulSoup(page.content, 'html.parser')
product_grid = soup.findAll('div', attrs={'class': 'product-grid__items'})
#print(product_grid)
products = []
for card in product_grid:
name = card.find('a', attrs={'class': 'product-card__link-overlay'})
products.append(name.text)
print(products)
Reutrns
['Nike Air VaporMax Flyknit 3']
Adidas
from bs4 import BeautifulSoup
import requests
import pandas as pd
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0'}
url = 'https://www.adidas.com/us/men-shoes'
page = requests.get(url, headers=headers)
if page.status_code == 200:
soup = BeautifulSoup(page.content, 'html5lib')
product_grid = soup.findAll('div', attrs={'class': 'product-container___3GvlZ'})
#print(product_grid)
products = []
for card in product_grid:
name = card.find('div', attrs={'class': 'gl-product-card__name'})
products.append(name.text)
print(products)
Returns
['NMD_R1 Shoes']

You can check the following code:
from bs4 import BeautifulSoup
import requests
import pandas as pd
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0'}
url = 'https://www.nike.com/w/mens-shoes-nik1zy7ok'
page = requests.get(url, headers=headers)
if page.status_code == 200:
soup = BeautifulSoup(page.content, 'html.parser')
product_grid = soup.findAll('div', attrs={'class': 'product-grid__items'})
products = []
for card in product_grid:
names = card.findAll('a', attrs={'class': 'product-card__link-overlay'})
for element in names:
products.append(element.text)
print(products)
The issue was in: name = card.find('a', attrs={'class': 'product-card__link-overlay'}).
If you print it out, you get a single name because you are doing .find not .findAll

How do I search within a website using the 'requests' module?

I want to search for different company names on the website. Website link: https://www.firmenwissen.de/index.html
On this website, I want to use the search engine and search companies. Here is the code I am trying to use:
from bs4 import BeautifulSoup as BS
import requests
import re
companylist = ['ABEX Dachdecker Handwerks-GmbH']
url = 'https://www.firmenwissen.de/index.html'
payloads = {
'searchform': 'UFT-8',
'phrase':'ABEX Dachdecker Handwerks-GmbH',
"mainSearchField__button":'submit'
}
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
html = requests.post(url, data=payloads, headers=headers)
soup = BS(html.content, 'html.parser')
link_list= []
links = soup.findAll('a')
for li in links:
link_list.append(li.get('href'))
print(link_list)
This code should bring me the next page with company information. But unfortunately, it returns only the home page. How can I do this?

Change your initial url you are doing search for. Grab the appropriate hrefs only and add to a set to ensure no duplicates (or alter selector to return only one match if possible); add those items to a final set for looping to ensure only looping required number of links. I have used Session on assumption you will repeat for many companies.
Iterate over the set using selenium to navigate to each company url and extract whatever info you need.
This is an outline.
from bs4 import BeautifulSoup as BS
import requests
from selenium import webdriver
d = webdriver.Chrome()
companyList = ['ABEX Dachdecker Handwerks-GmbH','SUCHMEISTEREI GmbH']
url = 'https://www.firmenwissen.de/ergebnis.html'
baseUrl = 'https://www.firmenwissen.de'
headers = {'User-Agent': 'Mozilla/5.0'}
finalLinks = set()
## searches section; gather into set
with requests.Session() as s:
for company in companyList:
payloads = {
'searchform': 'UFT-8',
'phrase':company,
"mainSearchField__button":'submit'
}
html = s.post(url, data=payloads, headers=headers)
soup = BS(html.content, 'lxml')
companyLinks = {baseUrl + item['href'] for item in soup.select("[href*='firmeneintrag/']")}
# print(soup.select_one('.fp-result').text)
finalLinks = finalLinks.union(companyLinks)
for item in finalLinks:
d.get(item)
info = d.find_element_by_css_selector('.yp_abstract_narrow')
address = d.find_element_by_css_selector('.yp_address')
print(info.text, address.text)
d.quit()
Just the first links:
from bs4 import BeautifulSoup as BS
import requests
from selenium import webdriver
d = webdriver.Chrome()
companyList = ['ABEX Dachdecker Handwerks-GmbH','SUCHMEISTEREI GmbH', 'aktive Stuttgarter']
url = 'https://www.firmenwissen.de/ergebnis.html'
baseUrl = 'https://www.firmenwissen.de'
headers = {'User-Agent': 'Mozilla/5.0'}
finalLinks = []
## searches section; add to list
with requests.Session() as s:
for company in companyList:
payloads = {
'searchform': 'UFT-8',
'phrase':company,
"mainSearchField__button":'submit'
}
html = s.post(url, data=payloads, headers=headers)
soup = BS(html.content, 'lxml')
companyLink = baseUrl + soup.select_one("[href*='firmeneintrag/']")['href']
finalLinks.append(companyLink)
for item in set(finalLinks):
d.get(item)
info = d.find_element_by_css_selector('.yp_abstract_narrow')
address = d.find_element_by_css_selector('.yp_address')
print(info.text, address.text)
d.quit()