How can I print any website content? (Using something like my code) - python

I want to open the website and get its content, store it in a variable and print it
from urllib.request import urlopen
url = any_website
content = urlopen(url).read().decode('utf-8')
print(content)
The expected result is that I get what is written in the page

In python, there are several libraries you may be interested in. An example of printing contents to get you started below:-
from bs4 import BeautifulSoup as soup
import requests
url = "https://en.wikipedia.org/wiki/List_of_multinational_corporations"
page = requests.get(url)
page_html = (page.content)
page_soup = soup(page_html, "html.parser")
print (page_soup)
with urlopen, you may try as below
from bs4 import BeautifulSoup
import urllib
url = "https://en.wikipedia.org/wiki/List_of_multinational_corporations"
r = urllib.urlopen(url).read()
soup = BeautifulSoup(r)
print type(soup)
print (soup.prettify()[0:1000])

Related

how to put web scraped data into a list

this is the code I used to get the data from a website with all the wordle possible words, im trying to put them in a list so I can create a wordle clone but I get a weird output when I do this. please help
import requests
from bs4 import BeautifulSoup
url = "https://raw.githubusercontent.com/tabatkins/wordle-list/main/words"
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
word_list = list(soup)
It do not need BeautifulSoup, simply split the text of the response:
import requests
url = "https://raw.githubusercontent.com/tabatkins/wordle-list/main/words"
requests.get(url).text.split()
Or if you like to do it wit BeautifulSoup anyway:
import requests
from bs4 import BeautifulSoup
url = "https://raw.githubusercontent.com/tabatkins/wordle-list/main/words"
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
soup.text.split()
Output:
['women',
'nikau',
'swack',
'feens',
'fyles',
'poled',
'clags',
'starn',...]

I would like to scrape multiple pages , but I got the result of the last url.Why?

Why does the result output the last url?
Is something wrong with my code?
import requests as uReq
from bs4 import BeautifulSoup as soup
import numpy as np
#can i use while loop instead for?
for page in np.arange(1,15):
url = uReq.get('https://www.myanmarbusiness-directory.com/en/categories-index/car-wheels-tyres-tubes-dealers/page{}.html?city=%E1%80%99%E1%80%9B%E1%80%99%E1%80%B9%E1%80%B8%E1%80%80%E1%80%AF%E1%80%94%E1%80%B9%E1%80%B8%E1%81%BF%E1%80%99%E1%80%AD%E1%80%B3%E1%82%95%E1%80%94%E1%80%9A%E1%80%B9'.format(page)).text
#have used for loop,but result is the last url
page_soup = soup(url,"html.parser")
info = page_soup.findAll("div",{"class: ","row detail_row"})
#Do all the url return output in one file?
filename = "wheel.csv"
file = open(filename,"w",encoding="utf-8")
you should check the indentation of what is happening after the for loop, otherwise, the variable url is replaced for every iteration of the loop, hence retaining only the last one.
import requests as uReq
from bs4 import BeautifulSoup as soup
import numpy as np
for page in np.arange(1,15):
url = uReq.get('https://www.myanmarbusiness-directory.com/en/categories-index/car-wheels-tyres-tubes-dealers/page{}.html?city=%E1%80%99%E1%80%9B%E1%80%99%E1%80%B9%E1%80%B8%E1%80%80%E1%80%AF%E1%80%94%E1%80%B9%E1%80%B8%E1%81%BF%E1%80%99%E1%80%AD%E1%80%B3%E1%82%95%E1%80%94%E1%80%9A%E1%80%B9'.format(page)).text
# this should be done N times (where N is the range param)
page_soup = soup(url,"html.parser")
info = page_soup.findAll("div",{"class: ","row detail_row"})
# append the results to the csv file
filename = "wheel.csv"
file = open(filename,"a",encoding="utf-8")
... # code for writing in the csv file
file.close()
Then, you will find everything in your file. Be aware that you should also close the file for saving it.
Try this!!
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen
import re
import requests
urls=['https://www.myanmarbusiness-directory.com/en/categories-index/car-wheels-tyres-tubes-dealers/page{}.html?city=%E1%80%99%E1%80%9B%E1%80%99%E1%80%B9%E1%80%B8%E1%80%80%E1%80%AF%E1%80%94%E1%80%B9%E1%80%B8%E1%81%BF%E1%80%99%E1%80%AD%E1%80%B3%E1%82%95%E1%80%94%E1%80%9A%E1%80%B9']
links = []
for url in urls:
response = requests.get(url)
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
html_page = urlopen(req).read()
soup = BeautifulSoup(html_page, features="html.parser")
for link in soup.select_one('ol.list_products').findAll('a', attrs={'href': re.compile("^([a-zA-Z0-9\-])+$")}):
links.append(link.get('href'))
filename = 'output.csv'
with open(filename, mode="w") as outfile:
for s in links:
outfile.write("%s\n" %s)

BS4 returns [] instead of the wanted HTML tag

I want to parse the given website and scrape the table. To me the code looks right. New to python and web parsing
import requests
from bs4 import BeautifulSoup
response = requests.get('https://delhifightscorona.in/')
doc = BeautifulSoup(response.text, 'lxml-xml')
cases = doc.find_all('div', {"class": "cell"})
print(cases)
doing this returns
[]
Change your parser and the class and there you have it.
import requests
from bs4 import BeautifulSoup
soup = BeautifulSoup(requests.get('https://delhifightscorona.in/').text, 'html.parser').find('div', {"class": "grid-x grid-padding-x small-up-2"})
print(soup.find("h3").getText())
Output:
423,831
You can choose to print only the cases or the total stats with the date.
import requests
from bs4 import BeautifulSoup
response = requests.get('https://delhifightscorona.in/')
doc = BeautifulSoup(response.text, 'html.parser')
stats = doc.find('div', {"class": "cell medium-5"})
print(stats.text) #Print the whole block with dates and the figures
cases = stats.find('h3')
print(cases.text) #Print the cases only

Get source from image from webpage

So I want to get the image source from this website:
https://www.pixiv.net/en/artworks/77619496
But every time I try to scrape it with bs4 I keep failing, I've tried other posts too but couldn't get it to work.
It keeps returning None
import requests
import bs4
from bs4 import BeautifulSoup
url = 'https://www.pixiv.net/en/artworks/77564597'
r = requests.get(url)
soup = BeautifulSoup(r.content, 'html.parser')
x = soup.find("img")
print(x)
If you look at chrome debug console's network section or the console in the browser you are browsing in, you should see that there is no img elements at the beginning, the page generates img elements by executing javascript. However, I inspected the page and there is a meta element which has image data in it and you can parse it with JSON as shown:
import requests, json
from bs4 import BeautifulSoup
url = 'https://www.pixiv.net/en/artworks/77564597'
r = requests.get(url)
soup = BeautifulSoup(r.content, 'html.parser')
x = soup.find("meta", {"id": "meta-preload-data"}).get("content")
usefulData = json.loads(x)
print(usefulData)
The sample output is here.
from selenium import webdriver
import time
from bs4 import BeautifulSoup
browser = webdriver.Firefox()
url = 'https://www.pixiv.net/en/artworks/77564597'
sada = browser.get(url)
time.sleep(3)
source = browser.page_source
soup = BeautifulSoup(source, 'html.parser')
for item in soup.findAll('div', attrs={'class': 'sc-fzXfPI fRnFme'}):
for img in item.findAll('img', attrs={'class': 'sc-fzXfPJ lclRkv'}):
print(img.get('src'))
Output:
https://i.pximg.net/c/250x250_80_a2/custom-thumb/img/2019/11/28/00/02/59/78026183_p0_custom1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/10/31/04/15/04/77564597_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/08/30/07/23/45/76528190_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/08/23/08/01/08/76410568_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/07/24/03/41/47/75881545_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/05/30/04/24/27/74969583_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/custom-thumb/img/2019/11/28/00/02/59/78026183_p0_custom1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/10/31/04/15/04/77564597_p0_square1200.jpg
https://i.pximg.net/c/250x250_80_a2/img-master/img/2019/08/30/07/23/45/76528190_p0_square1200.jpg

Reading in Content From URLS in a File

I'm trying to get other subset URLs from a main URL. However,as I print to see if I get the content, I noticed that I am only getting the HTML, not the URLs within it.
import urllib
file = 'http://example.com'
with urllib.request.urlopen(file) as url:
collection = url.read().decode('UTF-8')
I think this is what you are looking for.
You can use beautiful soup library of python and this code should work with python3
import urllib
from urllib.request import urlopen
from bs4 import BeautifulSoup
def get_all_urls(url):
open = urlopen(url)
url_html = BeautifulSoup(open, 'html.parser')
for link in url_html.find_all('a'):
links = str(link.get('href'))
if links.startswith('http'):
print(links)
else:
print(url + str(links))
get_all_urls('url.com')

Categories

Resources