How do i extract values with beautifulsoup? - python

Hi am using beautiful soup to extract the euro to us value, this is what i got so far:
import requests
from bs4 import BeautifulSoup
def Euro_spider():
url = 'http://fx-rate.net/USD/'
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, "html.parser")
what should i do next?

Now you need to locate the correct element containing the rate:
0.895
You can locate it, for example, by title:
usd_to_euro = soup.find(title="Dollar to Euro").get_text()
print(usd_to_euro) # prints 0.895

Related

How can I change the code to make it such that the html tags do not appear

from bs4 import BeautifulSoup
import requests
url = 'https://www.mediacorp.sg/en/your-mediacorp/our-artistes/tca/male-artistes/ayden-sng-12357686'
artiste_name = 'celeb-name'
page = requests.get(url)
soup = BeautifulSoup(page.text, 'lxml')
txt = soup.find_all('h1', attrs={'class':artiste_name})
print(txt)
with the above code, i get the output:
[<*h1 class="celeb-name">Ayden Sng</h1*>] #asterisks added to show h1 tags
What do i need to change in my code or how can i make it such that i only get 'Ayden Sng' as my output?
Iterate over each entry of the txt list and extract its txt property:
txt = [element.text for element in txt] # ['Ayden Sng']
Repl.it
from bs4 import BeautifulSoup
import requests
url = 'https://www.mediacorp.sg/en/your-mediacorp/our-artistes/tca/male-artistes/ayden-sng-12357686'
artiste_name = 'celeb-name'
page = requests.get(url)
soup = BeautifulSoup(page.text, 'lxml')
txt = soup.find_all('h1', attrs={'class':artiste_name})
print(txt[0].text)
if there are more than one reuslt you can use this code:
from bs4 import BeautifulSoup
import requests
url = 'https://www.mediacorp.sg/en/your-mediacorp/our-artistes/tca/male-artistes/ayden-sng-12357686'
artiste_name = 'celeb-name'
page = requests.get(url)
soup = BeautifulSoup(page.text, 'lxml')
txt = soup.find_all('h1', attrs={'class':artiste_name})
for i in txt:
print(i.text)

How do I make this web crawler print only the titles of the songs?

import requests
from bs4 import BeautifulSoup
url = 'https://www.officialcharts.com/charts/singles-chart'
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, 'html.parser')
urls = []
for link in soup.find_all('a'):
print(link.get('href'))
def chart_spider(max_pages):
page = 1
while page >= max_pages:
url = "https://www.officialcharts.com/charts/singles-chart"
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('a', {"class": "title"}):
href = "BAD HABITS" + link.title(href)
print(href)
page += 1
chart_spider(1)
Wondering how to make this print just the titles of the songs instead of the entire page. I want it to go through the top 100 charts and print all the titles for now. Thanks
Here's is a possible solution, which modify your code as little as possible:
#!/usr/bin/env python3
import requests
from bs4 import BeautifulSoup
URL = 'https://www.officialcharts.com/charts/singles-chart'
def chart_spider():
source_code = requests.get(URL)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for title in soup.find_all('div', {"class": "title"}):
print(title.contents[1].string)
chart_spider()
The result is a list of all the titles found in the page, one per line.
If all you want is the titles for each song on the top 100,
this code:
import requests
from bs4 import BeautifulSoup
url='https://www.officialcharts.com/charts/singles-chart/'
req = requests.get(url)
soup = BeautifulSoup(req.content, 'html.parser')
titles = [i.text.replace('\n', '') for i in soup.find_all('div', class_="title")]
does what you are looking for.
You can do like this.
The Song title is present inside a <div> tag with class name as title.
Select all those <div> with .find_all(). This gives you a list of all <div> tags.
Iterate over the list and print the text of each div.
from bs4 import BeautifulSoup
import requests
url = 'https://www.officialcharts.com/charts/singles-chart/'
r = requests.get(url)
soup = BeautifulSoup(r.text, 'lxml')
d = soup.find_all('div', class_='title')
for i in d:
print(i.text.strip())
Sample Output:
BAD HABITS
STAY
REMEMBER
BLACK MAGIC
VISITING HOURS
HAPPIER THAN EVER
INDUSTRY BABY
WASTED
.
.
.

Get html text with Beautiful Soup

I'm trying to get the number from inside a div:
<div class="tv-symbol-price-quote__value js-symbol-last">122.7<span class="">8</span></div>
I need the 122.7 number, but I cant get it. I have tried with:
strings = soup.find("div", class_="tv-symbol-price-quote__value js-symbol-last").string
But, there are more than one element and I receive "none".
Is there a way to print the childs and get the string from childs?
Use .getText().
For example:
from bs4 import BeautifulSoup
sample_html = """
<div class="tv-symbol-price-quote__value js-symbol-last">122.7<span class="">8</span></div>
"""
soup = BeautifulSoup(sample_html, "html.parser")
strings = soup.find("div", class_="tv-symbol-price-quote__value js-symbol-last").getText()
print(strings)
Output:
122.78
Or use __next__() to get only the 122.7.
soup = BeautifulSoup(sample_html, "html.parser")
strings = soup.find("div", class_="tv-symbol-price-quote__value js-symbol-last").strings.__next__()
print(strings)
Output:
122.7
To only get the first text, search for the tag, and call the next_element method.
from bs4 import BeautifulSoup
html = """
<div class="tv-symbol-price-quote__value js-symbol-last">122.7<span class="">8</span></div>
"""
soup = BeautifulSoup(html, "html.parser")
print(
soup.find("div", class_="tv-symbol-price-quote__value js-symbol-last").next_element
)
Output:
122.7
You could use selenium to find the element and then use BS4 to parse it.
An example would be
import selenium.webdriver as WD
from selenium.webdrive.chrome.options import Options
import bs4 as B
driver = WD.Chrome()
objXpath = driver.find_element_by_xpath("""yourelementxpath""")
objHtml = objXpath.get_attribute("outerHTML")
soup = B.BeutifulSoup(objHtml, 'html.parser')
text = soup.get_text()
This code should work.
DISCLAIMER
I haven't done work w/ selenium and bs4 in a while so you might have to tweak it a little bit.

How to skip or truncate character or symbols from text I need. Web-scraping with beautiful soup

I need to get price (61,990) between div tag but how can I get rid of currency symbol?
Same as here, I need to grab rating only (4.7), but I don't need anything after that, such that img src. How can I ignore it? Or skip it?
Code sample:
from bs4 import BeautifulSoup
import requests
price = []
ratings=[]
response = requests.get("https://www.flipkart.com/laptops/~buyback-guarantee-on-laptops-/pr?sid=6bo%2Cb5g&uniq")
soup = BeautifulSoup(response.text, 'html.parser')
for a in soup.findAll('a',href=True, attrs={'class':'_31qSD5'}):
price=a.find('div', attrs={'class':'_1vC4OE _2rQ-NK'})
rating=a.find('div', attrs={'class':'hGSR34'})
Here. You just need to use the .text method and treat it like a normal string. In this case, retain all but the first character.
from bs4 import BeautifulSoup
import requests
price = []
ratings=[]
response = requests.get("https://www.flipkart.com/laptops/~buyback-guarantee-on-laptops-/pr?sid=6bo%2Cb5g&uniq")
soup = BeautifulSoup(response.text, 'html.parser')
for a in soup.findAll('a',href=True, attrs={'class':'_31qSD5'}):
price=a.find('div', attrs={'class':'_1vC4OE _2rQ-NK'}).text[1:]
rating=a.find('div', attrs={'class':'hGSR34'}).text
print(price)
print(rating)
Out[110]: '4.3'
Out[111]: '52,990'

No output in console python

from bs4 import BeautifulSoup
import requests
def imdb_spider():
url = 'http://www.imdb.com/chart/top'
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a', {'class': 'secondaryInfo' }):
href = link.get('href')
print(href)
imdb_spider()
I'm trying to get links of all top rated movies from imdb . I'm using pycharm . The code runs for more than 30 mins but i'm not getting any print in my console.
You're correct that there's an element with class secondaryInfo for every movie title, but that's not the a element. If you want to find that, you have to use a different selector. For example, the following selector will do the trick instead of using soup.findAll().
soup.select('td.titleColumn a')
The problem is that {'class': 'secondaryInfo' } is a parameter of <span> object.
So try this:
from bs4 import BeautifulSoup
import requests
def imdb_spider():
url = 'http://www.imdb.com/chart/top'
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, "lxml")
for td in soup.findAll('td', {'class': 'titleColumn'}):
href = td.find('a').get('href')
print(href)
imdb_spider()

Categories