python beautifulsoup to download specific .zip files from a website - python

I am new to web scraping. I am trying to download only the weekly .zip files from the below website. I could able to parse the label and couldn't go beyond that to download the weekly zip files.
https://download.cms.gov/nppes/NPI_Files.html
html code for 'li' tag
import requests
from bs4 import BeautifulSoup
URL = "https://download.cms.gov/nppes/NPI_Files.html"
r = requests.get(URL)
#print(r.content)
soup = BeautifulSoup(r.content, 'html.parser')
#print(soup.prettify())
links=[]
ref = soup.select('li')
#print(ref)
for i in ref:


Try the next example
import requests
from bs4 import BeautifulSoup
URL = "https://download.cms.gov/nppes/NPI_Files.html"
r = requests.get(URL)
#print(r.content)
soup = BeautifulSoup(r.content, 'html.parser')
#print(soup.prettify())
links=[]
for ref in soup.select('div.bulletlistleft > ul > li')[2:]:
zip ='https://download.cms.gov/nppes'+ref.a.get('href').replace('./','/')
links.append(zip)
print(links)
Output:
['https://download.cms.gov/nppes/NPPES_Data_Dissemination_090522_091122_Weekly.zip', 'https://download.cms.gov/nppes/NPPES_Data_Dissemination_091222_091822_Weekly.zip', 'https://download.cms.gov/nppes/NPPES_Data_Dissemination_091922_092522_Weekly.zip']


Access a tags if there are any:
for i in ref:
if i.a is not None:
print(i.a.get('href'))


You can either just select all links then filter them down to the weekly updates:
ref = [
a for a in soup.select('a') if a.text
and 'Weekly Update' in a.text
]
OR you can narrow down to a parent element before selecting the links:
ref = soup.find(
'b', string='Weekly Incremental NPI Files'
).find_next('tr').select('a')
Either way, you'll end up with the same set of links:


The following code will find the links, download the files, and unzip them.
import requests
from bs4 import BeautifulSoup
import os
from urllib.request import urlretrieve
import zipfile
target_folder = os.path.dirname(os.path.realpath(__file__))
base_url = "https://download.cms.gov/nppes"
url = f"{base_url}/NPI_Files.html"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
elms = soup.select('div.bulletlistleft > ul > li > a')
for elm in elms:
zip_filename = elm.attrs['href'].lstrip('./')
zip_full_url = "/".join((base_url, zip_filename))
target_zip_path = os.path.join(target_folder, zip_filename)
target_zip_dir = ".".join(target_zip_path.split('.')[:-1])
urlretrieve(zip_full_url, target_zip_path)
with zipfile.ZipFile(target_zip_path, 'r') as zip_file:
zip_file.extractall(target_zip_dir)

Related

How to not print empty line?

I'm trying to scrap some links from a site but I'm running into an issue where my for loop will stop at the first link.
Currently What I have
import requests
import lxml
from bs4 import BeautifulSoup
url = 'http://ufcstats.com/statistics/fighters?char=a'
f = requests.get(url)
soup = BeautifulSoup(f.content, 'lxml')
fighter_links = soup.find('td', {
'class': 'b-statistics__table-col'
}).find_all('a')
fighterLinks = []
for anchor in fighter_links:
# urls = anchor['href']
fighterLinks.append(anchor['href'])
print(fighterLinks)
When I print I'm getting
['http://ufcstats.com/fighter-details/93fe7332d16c6ad9']
Site I'm trying to pull from

when you do
fighter_links = soup.find('td', {'class': 'b-statistics__table-col'}).find_all('a')
you are only getting the first table record. soup.find will only return the first match that it finds. what you need to do is change it to
fighter_links = soup.find_all('td', {'class': 'b-statistics__table-col'})
fighterLinks = []
that will get you all the table enteries that match your class name, and from there you need to do loop to extract out the links
for link in fighter_links:
if(link.find('a')):
fighterLinks.append(link.find('a').get('href'))

I don't know if this will help, but I hope it does:
import requests
from bs4 import BeautifulSoup
url = 'http://ufcstats.com/statistics/fighters?char=a'
f = requests.get(url)
soup = BeautifulSoup(f.content, 'lxml')
aa = soup.select("a.b-link_style_black")
fighterLinks = []
for i in aa:
for k in i:
fighterLinks.append(aa[aa.index(i)].attrs["href"])
print(fighterLinks)
outputs:
['http://ufcstats.com/fighter-details/93fe7332d16c6ad9', 'http://ufcstats.com/fighter-details/93fe7332d16c6ad9', 'http://ufcstats.com/fighter-details/15df64c02b6b0fde', 'http://ufcstats.com/fighter-details/15df64c02b6b0fde', 'http://ufcstats.com/fighter-details/15df64c02b6b0fde', 'http://ufcstats.com/fighter-details/59a9d6dac61c2540', 'http://ufcstats.com/fighter-details/59a9d6dac61c2540', 'http://ufcstats.com/fighter-details/b361180739bed4b0', 'http://ufcstats.com/fighter-details/b361180739bed4b0', 'http://ufcstats.com/fighter-details/b361180739bed4b0', 'http://ufcstats.com/fighter-details/3329d692aea4dc28', 'http://ufcstats.com/fighter-details/3329d692aea4dc28', 'http://ufcstats.com/fighter-details/3329d692aea4dc28', 'http://ufcstats.com/fighter-details/2f5cbecbbe18bac4', 'http://ufcstats.com/fighter-details/2f5cbecbbe18bac4', 'http://ufcstats.com/fighter-details/2f5cbecbbe18bac4', 'http://ufcstats.com/fighter-details/c0ed7b208197e8de', 'http://ufcstats.com/fighter-details/c0ed7b208197e8de', 'http://ufcstats.com/fighter-details/c0ed7b208197e8de', 'http://ufcstats.com/fighter-details/5140122c3eecd307', 'http://ufcstats.com/fighter-details/5140122c3eecd307', 'http://ufcstats.com/fighter-details/c9f6385af6df66d7', 'http://ufcstats.com/fighter-details/c9f6385af6df66d7', 'http://ufcstats.com/fighter-details/c9f6385af6df66d7', 'http://ufcstats.com/fighter-details/aa6e591c2a2cdecd', 'http://ufcstats.com/fighter-details/aa6e591c2a2cdecd', 'http://ufcstats.com/fighter-details/aa6e591c2a2cdecd', 'http://ufcstats.com/fighter-details/7279654c7674cd24', 'http://ufcstats.com/fighter-details/7279654c7674cd24', 'http://ufcstats.com/fighter-details/7279654c7674cd24', 'http://ufcstats.com/fighter-details/1c5879330d42255f', 'http://ufcstats.com/fighter-details/1c5879330d42255f', 'http://ufcstats.com/fighter-details/989b85f6540c86b1', 'http://ufcstats.com/fighter-details/989b85f6540c86b1', 'http://ufcstats.com/fighter-details/989b85f6540c86b1', 'http://ufcstats.com/fighter-details/2620f3eb21c79614', 'http://ufcstats.com/fighter-details/2620f3eb21c79614', 'http://ufcstats.com/fighter-details/83b00f7597e5ac83', 'http://ufcstats.com/fighter-details/83b00f7597e5ac83', 'http://ufcstats.com/fighter-details/83b00f7597e5ac83', 'http://ufcstats.com/fighter-details/a77633a989013265', 'http://ufcstats.com/fighter-details/a77633a989013265', 'http://ufcstats.com/fighter-details/a77633a989013265', 'http://ufcstats.com/fighter-details/79cb2a690b9ba5e8', 'http://ufcstats.com/fighter-details/79cb2a690b9ba5e8', 'http://ufcstats.com/fighter-details/79cb2a690b9ba5e8', 'http://ufcstats.com/fighter-details/1338e2c7480bdf9e', 'http://ufcstats.com/fighter-details/1338e2c7480bdf9e', 'http://ufcstats.com/fighter-details/1338e2c7480bdf9e', 'http://ufcstats.com/fighter-details/0e9869d712e81f8f', 'http://ufcstats.com/fighter-details/0e9869d712e81f8f', 'http://ufcstats.com/fighter-details/0e9869d712e81f8f', 'http://ufcstats.com/fighter-details/ebc5af72ad5a28cb', 'http://ufcstats.com/fighter-details/ebc5af72ad5a28cb', 'http://ufcstats.com/fighter-details/a08ddd04eaffd81d', 'http://ufcstats.com/fighter-details/a08ddd04eaffd81d', 'http://ufcstats.com/fighter-details/a08ddd04eaffd81d', 'http://ufcstats.com/fighter-details/44aa652b181bcf68', 'http://ufcstats.com/fighter-details/44aa652b181bcf68', 'http://ufcstats.com/fighter-details/501821d7fb7b95c1', 'http://ufcstats.com/fighter-details/501821d7fb7b95c1', 'http://ufcstats.com/fighter-details/6cadc0a0ba7dc015', 'http://ufcstats.com/fighter-details/6cadc0a0ba7dc015', 'http://ufcstats.com/fighter-details/6cadc0a0ba7dc015', 'http://ufcstats.com/fighter-details/8f382b3baa954d2a', 'http://ufcstats.com/fighter-details/8f382b3baa954d2a', 'http://ufcstats.com/fighter-details/8f382b3baa954d2a']

Requests will fail on some connections in this instance. Better use cloudscraper: (pip install cloudscraper)
import cloudscraper
from bs4 import BeautifulSoup
scraper = cloudscraper.create_scraper()
soup = BeautifulSoup(scraper.get("http://ufcstats.com/statistics/fighters?char=a").text)
links = soup.select_one('.b-statistics__table').select('a')
print(set([x.get('href') for x in links]))
This returns:
{'http://ufcstats.com/fighter-details/a08ddd04eaffd81d', 'http://ufcstats.com/fighter-details/15df64c02b6b0fde', 'http://ufcstats.com/fighter-details/a77633a989013265', 'http://ufcstats.com/fighter-details/0e9869d712e81f8f', 'http://ufcstats.com/fighter-details/1338e2c7480bdf9e', 'http://ufcstats.com/fighter-details/3329d692aea4dc28', 'http://ufcstats.com/fighter-details/79cb2a690b9ba5e8', 'http://ufcstats.com/fighter-details/44aa652b181bcf68', 'http://ufcstats.com/fighter-details/c0ed7b208197e8de', 'http://ufcstats.com/fighter-details/b361180739bed4b0', 'http://ufcstats.com/fighter-details/59a9d6dac61c2540', 'http://ufcstats.com/fighter-details/ebc5af72ad5a28cb', 'http://ufcstats.com/fighter-details/501821d7fb7b95c1', 'http://ufcstats.com/fighter-details/989b85f6540c86b1', 'http://ufcstats.com/fighter-details/7279654c7674cd24', 'http://ufcstats.com/fighter-details/aa6e591c2a2cdecd', 'http://ufcstats.com/fighter-details/8f382b3baa954d2a', 'http://ufcstats.com/fighter-details/2f5cbecbbe18bac4', 'http://ufcstats.com/fighter-details/93fe7332d16c6ad9', 'http://ufcstats.com/fighter-details/c9f6385af6df66d7', 'http://ufcstats.com/fighter-details/2620f3eb21c79614', 'http://ufcstats.com/fighter-details/5140122c3eecd307', 'http://ufcstats.com/fighter-details/83b00f7597e5ac83', 'http://ufcstats.com/fighter-details/6cadc0a0ba7dc015', 'http://ufcstats.com/fighter-details/1c5879330d42255f'}

How to get just links of articles in list using BeautifulSoup

Hey guess so I got as far as being able to add the a class to a list. The problem is I just want the href link to be added to the links_with_text list and not the entire a class. What am I doing wrong?
from bs4 import BeautifulSoup
from requests import get
import requests
URL = "https://news.ycombinator.com"
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')
results = soup.find(id = 'hnmain')
articles = results.find_all(class_="title")
links_with_text = []
for article in articles:
link = article.find('a', href=True)
links_with_text.append(link)
print('\n'.join(map(str, links_with_text)))
This prints exactly how I want the list to print but I just want the href from every a class not the entire a class. Thank you

To get all links from the https://news.ycombinator.com, you can use CSS selector 'a.storylink'.
For example:
from bs4 import BeautifulSoup
from requests import get
import requests
URL = "https://news.ycombinator.com"
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')
links_with_text = []
for a in soup.select('a.storylink'): # <-- find all <a> with class="storylink"
links_with_text.append(a['href']) # <-- note the ['href']
print(*links_with_text, sep='\n')
Prints:
https://blog.mozilla.org/futurereleases/2020/06/18/introducing-firefox-private-network-vpns-official-product-the-mozilla-vpn/
https://mxb.dev/blog/the-return-of-the-90s-web/
https://github.blog/2020-06-18-introducing-github-super-linter-one-linter-to-rule-them-all/
https://www.sciencemag.org/news/2018/11/why-536-was-worst-year-be-alive
https://www.strongtowns.org/journal/2020/6/16/do-the-math-small-projects
https://devblogs.nvidia.com/announcing-cuda-on-windows-subsystem-for-linux-2/
https://lwn.net/SubscriberLink/822568/61d29096a4012e06/
https://imil.net/blog/posts/2020/fakecracker-netbsd-as-a-function-based-microvm/
https://jepsen.io/consistency
https://tumblr.beesbuzz.biz/post/621010836277837824/advice-to-young-web-developers
https://archive.org/search.php?query=subject%3A%22The+Navy+Electricity+and+Electronics+Training+Series%22&sort=publicdate
https://googleprojectzero.blogspot.com/2020/06/ff-sandbox-escape-cve-2020-12388.html?m=1
https://apnews.com/1da061ce00eb531291b143ace0eed1c9
https://support.apple.com/library/content/dam/edam/applecare/images/en_US/appleid/android-apple-music-account-payment-none.jpg
https://standpointmag.co.uk/issues/may-june-2020/the-healing-power-of-birdsong/
https://steveblank.com/2020/06/18/the-coming-chip-wars-of-the-21st-century/
https://www.videolan.org/security/sb-vlc3011.html
https://onesignal.com/careers/2023b71d-2f44-4934-a33c-647855816903
https://www.bbc.com/news/world-europe-53006790
https://github.com/efficient/HOPE
https://everytwoyears.org/
https://www.historytoday.com/archive/natural-histories/intelligence-earthworms
https://cr.yp.to/2005-590/powerpc-cwg.pdf
https://quantum.country/
http://www.crystallography.net/cod/
https://parkinsonsnewstoday.com/2020/06/17/tiny-magnetically-powered-implant-may-be-future-of-deep-brain-stimulation/
https://spark.apache.org/releases/spark-release-3-0-0.html
https://arxiv.org/abs/1712.09624
https://www.washingtonpost.com/technology/2020/06/18/data-privacy-law-sherrod-brown/
https://blog.chromium.org/2020/06/improving-chromiums-browser.html

Retrieving content using Beautifulsoup and selectors

Trying to retrieve content (text) embedded in html. Not getting the content.
Trying to use selector in the format to find price_box:
price_box = soup2.find('div', attrs={'title class': 'Fw(600)'})
# Import libraries
import requests
import urllib.request
import time
from bs4 import BeautifulSoup
# Set the URL you want to webscrape from
url = 'https://finance.yahoo.com/quote/NVDA?p=NVDA'
# Connect to the URL
response = requests.get(url)
# Parse HTML and save to BeautifulSoup object¶
soup = BeautifulSoup(response.text, "html.parser")
beta = soup.find('h1')
#print (beta)
link = beta.contents
variable = 'NVDA - NVIDIA Corporation'
test = 'NVDA - NVIDIA Corporation'
#<..>
url2 = 'https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01'
response2 = requests.get(url2)
soup2 = BeautifulSoup(response2.text, "html.parser")
# alpha = soup2.find('')
# div = soup.find('a', {class_ ='D(ib) '})
# text = div.string
price_box = soup2.find('div', attrs={'title class': 'Fw(600)'})
#price = price_box.text
print("Price Box: "+ str(price_box)) # THIS IS WHAT I WANT
Was hoping to see "Senea". Instead seeing "None" - "Price Box:
None"

A lot of the content is dynamic. You can regex out that info easily
import requests, re
p = re.compile(r'"YFINANCE:(.*?)"')
r = requests.get('https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01&guccounter=1')
print(p.findall(r.text)[0])
An alternate is to avoid the dynamic looking classes altogether
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('https://finance.yahoo.com/calendar/earnings?from=2019-09-01&to=2019-09-07&day=2019-09-01&guccounter=1')
soup = bs(r.content, 'lxml')
print(soup.select_one('#cal-res-table a').text)
Reading:
css selectors

Problems retrieving information from imdb

I'm trying to get the movie titles from an imdb watchlist. This is my code:
import requests, bs4
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
print(soup.find_all('.lister-item-header'))
Even though '.lister-item-header' exists in the chrome developer console it doesn't exist in the html file that the requests module downloaded. I've also tried using regular expressions. What would be the best way of retrieving the titles?

You should select elements by their class in this way.
import requests
import bs4
url = 'http://www.imdb.com/chart/top'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
rows = soup.select('.titleColumn > a')
for row in rows:
print(row.text)
Or you can do it in this way:
import requests
import bs4
url = 'http://www.imdb.com/chart/top'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
rows = soup.find_all('td', class_='titleColumn')
for row in rows:
print(row.a.text)
The data is load from a json object which is embedded into the raw html file, so we can parse it and get the title.
import requests
import bs4
import json
url = 'http://www.imdb.com/user/ur69187878/watchlist?ref_=wt_nv_wl‌​_all_1'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, "html.parser")
# rows = soup.find_all('h3', class_='list-item-header')
js_elements = soup.find_all('script')
js_text = None
search_str = 'IMDbReactInitialState.push('
for element in js_elements:
text = element.text
if search_str in text:
js_text = text.strip()
break
json_start = js_text.index(search_str) + len(search_str)
json_text = js_text[json_start:-2]
json_obj = json.loads(js_text[json_start:-2])
for title in json_obj['titles']:
json_title = json_obj['titles'][title]
print(json_title['primary']['title'])
But I have to say that this is not a general method to attack this kind of problems, if you wanna have a general solution for all pages whose data is loaded from json or api, you can use some other ways such as Selenium.

Scrape Multiple URLs using Beautiful Soup

I'm trying to extract specific classes from multiple URLs. The tags and classes stay the same but I need my python program to scrape all as I just input my link.
Here's a sample of my work:
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
url = input('insert URL here: ')
#scrape elements
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
This works for individual URLs but not for a batch. Thanks for helping me. I learned a lot from this community.

Have a list of urls and iterate through it.
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
urls = ['www.website1.com', 'www.website2.com', 'www.website3.com', .....]
#scrape elements
for url in urls:
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
If you are going to prompt user for input for each site then it can be done this way
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
urls = ['www.website1.com', 'www.website2.com', 'www.website3.com', .....]
#scrape elements
msg = 'Enter Url, to exit type q and hit enter.'
url = input(msg)
while(url!='q'):
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
#print titles only
h1 = soup.find("h1", class_= "class-headline")
print(h1.get_text())
input(msg)

If you want to scrape links in batches. Specify a batch size and iterate over it.
from bs4 import BeautifulSoup
import requests
import pprint
import re
import pyperclip
batch_size = 5
urllist = ["url1", "url2", "url3", .....]
url_chunks = [urllist[x:x+batch_size] for x in xrange(0, len(urllist), batch_size)]
def scrape_url(url):
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
h1 = soup.find("h1", class_= "class-headline")
return (h1.get_text())
def scrape_batch(url_chunk):
chunk_resp = []
for url in url_chunk:
chunk_resp.append(scrape_url(url))
return chunk_resp
for url_chunk in url_chunks:
print scrape_batch(url_chunk)

Categories

Resources