WebScraping using python - python

I'm scraping all the comments from https://www.consumeraffairs.com/privacy/transunion.html website
page_list = []
def pagination(soup):
for i in range(0,32):
domain = "https://www.consumeraffairs.com/privacy/transunion.html?page="+str(i)
page_list.append(domain)
return page_list
pages = pagination(soup)
print(pages)
how to capture the comments under these pages as it shows
import time
comment_list = []
def get_comments(urls):
for url in urls:
try:
print(url)
#comment = soup.find_all('div',{'class':'rvw-bd'})
comment = soup.find_all('div',{'class':'rvw-bd'})
print(len(comment))
for x in range(len(comment)):
comment_list.append(comment[x].p.text.strip())
except:
continue
time.sleep(30)
return comment_list
comments = get_comments(pages)
I used this code but it scraps only first 10 in first page. how to fix this

I think you were on the right track changing the "page=" value in the url, but from the code you posted, it doesn't seem like you changed the soup object to represent the content of each new page. I rewrote some of your code to do this:
from bs4 import BeautifulSoup
import requests
import time
page_list = []
for i in range(0,32):
domain = "https://www.consumeraffairs.com/privacy/transunion.html?page="+str(i)
page_list.append(domain)
comment_list = []
for page in page_list:
try:
content = requests.get(page).content
soup = BeautifulSoup(content, 'html.parser')
#comment = soup.find_all('div',{'class':'rvw-bd'})
comment = soup.find_all('div',{'class':'rvw-bd'})
print(len(comment))
for x in range(len(comment)):
comment_list.append(comment[x].p.text.strip())
except:
continue
time.sleep(30)
print(comment_list)
print(len(comment_list))
Let me know if this does/doesn't help!

Related

scraping links from wikipedia

So i am trying to scrape links from a random wikipedia page here is my code thus far:
from bs4 import BeautifulSoup
import requests
import pandas as pd
import urllib2
# function get random page
def get_random():
import requests
# r = requests.get('https://en.wikipedia.org/wiki/Special:Random')
r = requests.get('https://en.wikipedia.org/wiki/Carole_Ann')
return r.url
#========================
#finding the valid link
def validlink(href):
if href:
if re.compile('^/wiki/').search(href):
if not re.compile('/\w+:').search(href):
return True
return False
#validlink()===========
#the first site
a1 = get_random()
#print("the first site is: " + a1)
# the first site end()====
#looking for the article name:
blin = requests.get(a1)
soup = BeautifulSoup(blin.text, 'html.parser')
title = soup.find('h1', {'class' : 'firstHeading'})
print("starting website: " + a1 + " Titled: " + title.text)
print("")
#=============================
#first article done
#find body:
import re
body = requests.get(a1).text
soup = BeautifulSoup(body, 'lxml')
for link in soup.findAll("a"):
url = link.get("href", "")
print(
#======================
i know i'm doing this last part wrong. Im new to python so i just have no idea how to go about this part, what i need is to pull all of the links from a random site that the random page takes me to, then i pull the link and title off of that site,
then i need to pull the wikipedia links off of that page which is what i am looking to do in that last bit of code there heres another snip:
and at this point i want to print all of the links that it finds after they have been tested against my valid links function at the top:
again forgive me for being new and not understanding at this. But please help i cannot figure this out.
so the question that i have is: i need to create a snippet of code that will pull out all of the website links off of the wikipedia page (which note i still dont know how to do the for loop was my best guess based on my own research) then i need to test the links that i pulled against my validlink function, and print out all of the valid links.
If you whan it as list then create new list and append() url if it is valid.
Because the same url can be many times on page so I also check if url is already on list.
valid_urls = []
for link in soup.find_all('a'): # find_all('a', {'href': True}):
url = link.get('href', '')
if url not in valid_urls and validlink(url):
valid_urls.append(url)
print(valid_urls)
from bs4 import BeautifulSoup
import requests
import re
# --- functions ---
def is_valid(url):
"""finding the valid link"""
if url:
if url.startswith('/wiki/'): # you don't need `re` to check it
if not re.compile('/\w+:').search(url):
return True
return False
# --- main ---
#random_url = 'https://en.wikipedia.org/wiki/Special:Random'
random_url = 'https://en.wikipedia.org/wiki/Carole_Ann'
r = requests.get(random_url)
print('url:', r.url)
soup = BeautifulSoup(r.text, 'html.parser')
title = soup.find('h1', {'class': 'firstHeading'})
print('starting website:', r.url)
print('titled:', title.text)
print()
valid_urls = []
for link in soup.find_all('a'): # find_all('a', {'href': True}):
url = link.get('href', '')
if url not in valid_urls and is_valid(url):
valid_urls.append(url)
#print(valid_urls)
#for url in valid_urls:
# print(url)
print('\n'.join(valid_urls))

Scraping each element from website with BeautifulSoup

I wrote a code for scraping one real estate website. This is the link:
https://www.nekretnine.rs/stambeni-objekti/stanovi/lista/po-stranici/10/
From this page I can get only location, size and price of the apartment, but Is it possible to write a code that will go on page of each appartment and scrape values from it, because it contains much more info. Check this link:
https://www.nekretnine.rs/stambeni-objekti/stanovi/arena-bulevar-arsenija-carnojevica-97m-2-lode-energoprojekt/NkvJK0Ou5tV/
I have posted a code. I noticed that my url changes when I click on specific real estate. For example:
arena-bulevar-arsenija-carnojevica-97m-2-lode-energoprojekt/NkvJK0Ou5tV/
I taught about creating for loop, but there is no way to know how it changes because it has some id number at the end:
NkvJK0Ou5tV
This is the code that I have:
from bs4 import BeautifulSoup
import requests
website = "https://www.nekretnine.rs/stambeni-objekti/stanovi/lista/po-stranici/10/"
soup = requests.get(website).text
my_html = BeautifulSoup(soup, 'lxml')
lokacija = my_html.find_all('p', class_='offer-location text-truncate')
ukupna_kvadratura = my_html.find_all('p', class_='offer-price offer-price--invert')
ukupna_cena = my_html.find_all('div', class_='d-flex justify-content-between w-100')
ukupni_opis = my_html.find_all('div', class_='mt-1 mb-1 mt-lg-0 mb-lg-0 d-md-block offer-meta-info offer-adress')
for lok, kvadratura, cena_stana, sumarno in zip(lokacija, ukupna_kvadratura, ukupna_cena, ukupni_opis):
lok = lok.text.split(',')[0] #lokacija
kv = kvadratura.span.text.split(' ')[0] #kvadratura
jed = kvadratura.span.text.split(' ')[1] #jedinica mere
cena = cena_stana.span.text #cena
sumarno = sumarno.text
datum = sumarno.split('|')[0].strip()
status = sumarno.split('|')[1].strip()
opis = sumarno.split('|')[2].strip()
print(lok, kv, jed, cena, datum, status, opis)
You can get href from div class="placeholder-preview-box ratio-4-3".
From here you can find the URL.
You can iterate over the links provided by the pagination at the bottom of the page:
from bs4 import BeautifulSoup as soup
import requests
d = soup(requests.get('https://www.nekretnine.rs/stambeni-objekti/stanovi/lista/po-stranici/10/').text, 'html.parser')
def scrape_page(page):
return [{'title':i.h2.get_text(strip=True), 'loc':i.p.get_text(strip=True), 'price':i.find('p', {'class':'offer-price'}).get_text(strip=True)} for i in page.find_all('div', {'class':'row offer'})]
result = [scrape_page(d)]
while d.find('a', {'class':'pagination-arrow arrow-right'}):
d = soup(requests.get(f'https://www.nekretnine.rs{d.find("a", {"class":"pagination-arrow arrow-right"})["href"]}').text, 'html.parser')
result.append(scrape_page(d))

How to scrape embedded integers on a website

I'm trying to scrape the number of likes for the datasets available on this website.
I've been unable to workout a way of reliably identifying and scraping the relationship between the dataset title and the like integer:
as it is embedded in the HTML as below:
I have used a scraper previously to get information about the resource urls. In that case I was able to capture the last child a of parent h3 with a parent having class .dataset-item.
I would like to adapt my existing code to scrape the number of likes for each resource in the catalogue, rather than the URLs. Below is the code for the url scraper I used:
from bs4 import BeautifulSoup as bs
import requests
import csv
from urllib.parse import urlparse
json_api_links = []
data_sets = []
def get_links(s, url, css_selector):
r = s.get(url)
soup = bs(r.content, 'lxml')
base = '{uri.scheme}://{uri.netloc}'.format(uri=urlparse(url))
links = [base + item['href'] if item['href'][0] == '/' else item['href'] for item in soup.select(css_selector)]
return links
results = []
#debug = []
with requests.Session() as s:
for page in range(1,2): #set number of pages
links = get_links(s, 'https://data.nsw.gov.au/data/dataset?page={}'.format(page), '.dataset-item h3 a:last-child')
for link in links:
data = get_links(s, link, '[href*="/api/3/action/package_show?id="]')
json_api_links.append(data)
#debug.append((link, data))
resources = list(set([item.replace('opendata','') for sublist in json_api_links for item in sublist])) #can just leave as set
for link in resources:
try:
r = s.get(link).json() #entire package info
data_sets.append(r)
title = r['result']['title'] #certain items
if 'resources' in r['result']:
urls = ' , '.join([item['url'] for item in r['result']['resources']])
else:
urls = 'N/A'
except:
title = 'N/A'
urls = 'N/A'
results.append((title, urls))
with open('data.csv','w', newline='') as f:
w = csv.writer(f)
w.writerow(['Title','Resource Url'])
for row in results:
w.writerow(row)
My desired output would appear like this:
The approach is pretty straight forward. Your given website contains required elements in a list Tag. And what you need to do, is to get source code of that <li> tag, and just fetch Heading, which has a certain class and Same goes for like count.
The catch in like count is, the text comprises of some noise. To fix that, you can use regular expression to extract digits ('\d+') from given input of likes count. Following code gives desired result:
from bs4 import BeautifulSoup as soup
import requests
import re
import pandas as pd
source = requests.get('https://data.nsw.gov.au/data/dataset')
sp = soup(source.text,'lxml')
element = sp.find_all('li',{'class':"dataset-item"})
heading = []
likeList = []
for i in element:
try:
header = i.find('a',{'class':"searchpartnership-url-analytics"})
heading.append(header.text)
except:
header = i.find('a')
heading.append(header.text)
like = i.find('span',{'id':'likes-count'})
likeList.append(re.findall('\d+',like.text)[0])
dict = {'Title': heading, 'Likes': likeList}
df = pd.DataFrame(dict,index=False)
print(df)
Hope it helped!
You could use the following.
I am using a css selector with Or syntax to retrieve title and likes as one list (as every publication has both). I then use slicing to separate titles from likes.
from bs4 import BeautifulSoup as bs
import requests
import csv
def get_titles_and_likes(s, url, css_selector):
r = s.get(url)
soup = bs(r.content, 'lxml')
info = [item.text.strip() for item in soup.select(css_selector)]
titles = info[::2]
likes = info[1::2]
return list(zip(titles,likes))
results = []
with requests.Session() as s:
for page in range(1,10): #set number of pages
data = get_titles_and_likes(s, 'https://data.nsw.gov.au/data/dataset?page={}'.format(page), '.dataset-heading .searchpartnership-url-analytics, .dataset-heading [href*="/data/dataset"], .dataset-item #likes-count')
results.append(data)
results = [i for item in results for i in item]
with open(r'data.csv','w', newline='') as f:
w = csv.writer(f)
w.writerow(['Title','Likes'])
for row in results:
w.writerow(row)

pagination : why it's still run while the page is not match?

I want to scrape data from a website, but first I want to get the page with pagination. Here I'm using python as a program language, and I already got this code. But when I run it, it doesn't work properly. the result must be stopped when response.url didn't match with expected_url. Is there someone know how to solve it? Please help, thank you.
Here is the code :
from bs4 import BeautifulSoup
import urllib.request
count = 0
url = "http://www.belanjamimo.net/foundation-bb-cream/?o=a&s=%d"
def get_url(url):
req = urllib.request.Request(url)
return urllib.request.urlopen(req)
expected_url = url % count
response = get_url(expected_url)
while (response.url == expected_url):
print("GET {0}".format(expected_url))
count += 9
expected_url = url % count
response = get_url(expected_url)
Try the below approach to exhaust all the items in different pages and break out of loop when there is no more items available.
from bs4 import BeautifulSoup
import requests
url = "http://www.belanjamimo.net/foundation-bb-cream/?o=a&s={}"
page = 0
while True:
res = requests.get(url.format(page))
soup = BeautifulSoup(res.text,"lxml")
items = soup.select(".product-block h2 a")
if len(items)<=1:break #check out if there is any product still available
for item in items:
print(item.text)
page+=9

How to scrape text from div with empty class value

Hi how to scrape text from div without any class? At first I try to scrape all data from div with class 'jobs page' then without class value but it doesn't work.
from bs4 import BeautifulSoup
import requests
a = {}
def antal_pl(name=''):
try:
page_response = requests.get('https://antal.pl/oferty-pracy?s=&sid=&did=Accountancy', timeout=40).text
page_content = BeautifulSoup(page_response, 'lxml')
data = page_content.find_all(class_ = 'jobs_page')
data_in = data.find_all('div', class_ = None)
print(data_in)
except:
''
antal_pl( name='Accontancy')
Try the below approach to get the text out of that webpage as you mentioned above. I've tried to organize your code a little to make it look cleaner.
from bs4 import BeautifulSoup
import requests
URL = "https://antal.pl/oferty-pracy?s=&sid=&did={}"
def antal_pl(name):
res = requests.get(URL.format(name))
soup = BeautifulSoup(res.text, 'lxml')
data = soup.find(class_='header').find_next_sibling().text.strip()
print(data)
if __name__ == '__main__':
antal_pl("Accountancy")
Result:
Znaleziono 47 ofert pracy.
use XPATH
html = etree.HTML(wb_data)
html_data = html.xpath('/html/body/div/ul/li/a')
enter image description here

Categories

Resources