How do I get rid of part of an object / Dictionary? [duplicate] - python

This question already has answers here:
What is the purpose of the return statement? How is it different from printing?
(15 answers)
Closed 8 months ago.
I'm web scraping a site for data using beautifulsoup4, and I'm not sure how to be specific to the data I want, without calling an unwanted object. I've failed to get rid of it.
import requests
from bs4 import BeautifulSoup
headers = {'User-agent': 'Mozilla/5.0 (Windows 10; Win64; x64; rv:101.0.1) Gecko/20100101 Firefox/101.0.1'}
url = "https://elitejobstoday.com/job-category/education-jobs-in-uganda/"
r = requests.get(url, headers = headers)
c = r.content
soup = BeautifulSoup(c, "html.parser")
table = soup.find("div", attrs={"article": "loadmore-item"})
def jobScan(link):
the_job = {}
job = requests.get(url, headers = headers)
jobC = job.content
jobSoup = BeautifulSoup(jobC, "html.parser")
name = jobSoup.find("h3", attrs={"class": "loop-item-title"})
title = name.a.text
the_job['title'] = title
print('The job is: {}'.format(title))
print(the_job)
return the_job
jobScan(table)
this is the result it fetches
PS C:\Users\MUHUMUZA IVAN\Desktop\JobPortal> py absa.py
The job is: 25 Credit Officers (Group lending) at ENCOT Microfinance Ltd
{'urlLink': 'https://elitejobstoday.com/job-category/education-jobs-in-uganda/', 'title': '25 Credit Officers (Group lending) at ENCOT Microfinance Ltd'}
I want to be able to retain "The job is: 25 Credit Officers (Group lending) at ENCOT Microfinance Ltd" and drop "{'urlLink': 'https://elitejobstoday.com/job-category/education-jobs-in-uganda/', 'title': '25 Credit Officers (Group lending) at ENCOT Microfinance Ltd'}"

if you just want the desired output to be printed, you don't need the dicitonary or any return. just print the title and remove the second print.
import requests
from bs4 import BeautifulSoup
headers = {'User-agent': 'Mozilla/5.0 (Windows 10; Win64; x64; rv:101.0.1) Gecko/20100101 Firefox/101.0.1'}
url = "https://elitejobstoday.com/job-category/education-jobs-in-uganda/"
r = requests.get(url, headers=headers)
c = r.content
soup = BeautifulSoup(c, "html.parser")
table = soup.find("div", attrs={"article": "loadmore-item"})
def jobScan(link):
job = requests.get(url, headers=headers)
jobC = job.content
jobSoup = BeautifulSoup(jobC, "html.parser")
name = jobSoup.find("h3", attrs={"class": "loop-item-title"})
title = name.a.text
print('The job is: {}'.format(title))
jobScan(table)

Related

Web scrape using Python - Execution takes too long

I am trying to webscrape the "Active Positions" table from the following website:
https://www.nasdaq.com/market-activity/stocks/aapl/institutional-holdings
My code is below:
from bs4 import BeautifulSoup
import requests
html_text = requests.get('https://www.nasdaq.com/market-activity/stocks/aapl/institutional-holdings')
soup = BeautifulSoup(html_text, 'lxml')
job1 = soup.find('div', classs_ = 'dialog-off-canvas-main-canvas')
job2 = job1.find('div', class_ = 'page with-primary-nav hide-more-videos')
job3 = job2.find('div', class_ = 'page__main')
job4 = job3.find('div', class_ = 'page__content')
job5 = job4.find('div', class_ = 'quote-subdetail__content quote-subdetail__content--new')
job6 = job5.findAll('div', class_ = 'layout layout--2-col-large')
job7 = job6.find('div', class_ = 'institutional-holdings institutional-holdings--paginated')
job8 = job7.find('div', class_ = 'institutional-holdings__section institutional-holdings__section--active-positions')
job9 = job8.find('div', class_ = 'institutional-holdings__table-container')
job10 = job9.find('table', class_ = 'institutional-holdings__table')
job11 = job10.find('tbody', class_ = 'institutional-holdings__body')
job12 = job11.findAll('tr', class_ = 'institutional-holdings__row').text
print(job12)
I have chosen to include nearly every class path to attempt to speed up the execution, as including only a couple took up to 10 minutes before i decided to interupt. However, i still get the same long execution with no output. Is there something wrong with my code? Or can I improve this by doing something I haven't thought of? Thanks.
Data is being hydrated in page via Javascript XHR calls. Here is a way of getting ActivePositions by scraping the API endpoint directly:
import requests
import pandas as pd
url = 'https://api.nasdaq.com/api/company/AAPL/institutional-holdings?limit=15&type=TOTAL&sortColumn=marketValue&sortOrder=DESC'
headers = {
'accept': 'application/json, text/plain, */*',
'origin': 'https://www.nasdaq.com',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36'
}
r = requests.get(url, headers=headers)
df = pd.json_normalize(r.json()['data']['activePositions']['rows'])
print(df)
Result in terminal:
positions holders shares
0 Increased Positions 1,780 239,170,203
1 Decreased Positions 2,339 209,017,331
2 Held Positions 283 8,965,339,255
3 Total Institutional Shares 4,402 9,413,526,789
In case you want to scrape the big 4,402 Institutional Holders table, there are ways for that too.
EDIT: Here is how you can save the data to a json file:
df.to_json('active_positions.json')
Although it might make more sense to save it as tabular data (csv):
df.to_csv('active_positions.csv')
Pandas docs: https://pandas.pydata.org/docs/

how to scrape page inside the result card using Bs4?

<img class="no-img" data-src="https://im1.dineout.co.in/images/uploads/restaurant/sharpen/4/h/u/p4059-15500352575c63a9394c209.jpg?tr=tr:n-medium" alt="Biryani By Kilo" data-gatype="RestaurantImageClick" data-url="/delhi/biryani-by-kilo-connaught-place-central-delhi-40178" data-w-onclick="cardClickHandler" src="https://im1.dineout.co.in/images/uploads/restaurant/sharpen/4/h/u/p4059-15500352575c63a9394c209.jpg?tr=tr:n-medium">
page url - https://www.dineout.co.in/delhi-restaurants?search_str=biryani&p=1
this page contains some restaurants card now while scrapping the page in the loop I want to go inside the restaurant card URL which is in the above HTML code name by data-url class and scrape the no. of reviews from inside it, I don't know how to do it my current code for normal front page scrapping is ;
def extract(page):
url = f"https://www.dineout.co.in/delhi-restaurants?search_str=biryani&p={page}" # URL of the website
header = {'User-Agent':'Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36'} # Temporary user agent
r = requests.get(url, headers=header)
soup = BeautifulSoup(r.content, 'html.parser')
return soup
def transform(soup): # function to scrape the page
divs = soup.find_all('div', class_ = 'restnt-card restaurant')
for item in divs:
title = item.find('a').text.strip() # restaurant name
loc = item.find('div', class_ = 'restnt-loc ellipsis').text.strip() # restaurant location
try: # used this try and except method because some restaurants are unrated and while scrpaping those we would run into an error
rating = item.find('div', class_="img-wrap").text
rating = (re.sub("[^0-9,.]", "", rating))
except:
rating = None
pricce = item.find('span', class_="double-line-ellipsis").text.strip() # price for biriyani
price = re.sub("[^0-9]", "", pricce)[:-1]
biry_del = {
'name': title,
'location': loc,
'rating': rating,
'price': price
}
rest_list.append(biry_del)
rest_list = []
for i in range(1,18):
print(f'getting page, {i}')
c = extract(i)
transform(c)
I hope you guys understood please ask in comment for any confusion.
It's not very fast but it looks like you can get all the details you want including the review count (not 232!) if you hit this backend api endpoint:
https://www.dineout.co.in/get_rdp_data_main/delhi/69676/restaurant_detail_main
import requests
from bs4 import BeautifulSoup
import pandas as pd
rest_list = []
for page in range(1,3):
print(f'getting page, {page}')
s = requests.Session()
url = f"https://www.dineout.co.in/delhi-restaurants?search_str=biryani&p={page}" # URL of the website
header = {'User-Agent':'Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36'} # Temporary user agent
r = s.get(url, headers=header)
soup = BeautifulSoup(r.content, 'html.parser')
divs = soup.find_all('div', class_ = 'restnt-card restaurant')
for item in divs:
code = item.find('a')['href'].split('-')[-1] # restaurant code
print(f'Getting details for {code}')
data = s.get(f'https://www.dineout.co.in/get_rdp_data_main/delhi/{code}/restaurant_detail_main').json()
info = data['header']
info.pop('share') #clean up csv
info.pop('options')
rest_list.append(info)
df = pd.DataFrame(rest_list)
df.to_csv('dehli_rest.csv',index=False)

Why can't I scrape Amazon products by BeautifulSoup?

I am trying to scrape the heading of this Amazon listing. The code I wrote is working for some other Amazon listings, but not working for the url mentioned in the code below.
Here is the python code I've tried:
import requests
from bs4 import BeautifulSoup
url="https://www.amazon.in/BULLMER-Cotton-Printed-T-shirt-Multicolour/dp/B0892SZX7F/ref=sr_1_4?c=ts&dchild=1&keywords=Men%27s+T-Shirts&pf_rd_i=1968024031&pf_rd_m=A1VBAL9TL5WCBF&pf_rd_p=8b97601b-3643-402d-866f-95cc6c9f08d4&pf_rd_r=EPY70Y57HP1220DK033Y&pf_rd_s=merchandised-search-6&qid=1596817115&refinements=p_72%3A1318477031&s=apparel&sr=1-4&ts_id=1968123031"
headers = {"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:79.0) Gecko/20100101 Firefox/79.0"}
page = requests.get(url, headers=headers)
print(page.status_code)
soup = BeautifulSoup(page.content, "html.parser")
#print(soup.prettify())
title = soup.find(id = "productTitle")
if title:
title = title.get_text()
else:
title = "default_title"
print(title)
Output:
200
default_title
html code from inspector tools:
<span id="productTitle" class="a-size-large product-title-word-break">
BULLMER Mens Halfsleeve Round Neck Printed Cotton Tshirt - Combo Tshirt - Pack of 3
</span>
First, As others have commented, use a proxy service. Second in order to go amazon product page if you have an asin that's enough.
Amazon follows this url pattern for all product pages.
https://www.amazon.(com/in/fr)/dp/<asin>
import requests
from bs4 import BeautifulSoup
url="https://www.amazon.in/dp/B0892SZX7F"
headers = {'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36'}
page = requests.get(url, headers=headers)
print(page.status_code)
soup = BeautifulSoup(page.content, "html.parser")
title = soup.find("span", {"id":"productTitle"})
if title:
title = title.get_text(strip=True)
else:
title = "default_title"
print(title)
Output:
200
BULLMER Mens Halfsleeve Round Neck Printed Cotton Tshirt - Combo Tshirt - Pack of 3
this worked fine for me:
import requests
from bs4 import BeautifulSoup
url="https://www.amazon.in/BULLMER-Cotton-Printed-T-shirt-Multicolour/dp/B0892SZX7F/ref=sr_1_4?c=ts&dchild=1&keywords=Men%27s+T-Shirts&pf_rd_i=1968024031&pf_rd_m=A1VBAL9TL5WCBF&pf_rd_p=8b97601b-3643-402d-866f-95cc6c9f08d4&pf_rd_r=EPY70Y57HP1220DK033Y&pf_rd_s=merchandised-search-6&qid=1596817115&refinements=p_72%3A1318477031&s=apparel&sr=1-4&ts_id=1968123031"
headers = {"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:79.0) Gecko/20100101 Firefox/79.0"}
http_proxy = "http://10.10.1.10:3128"
https_proxy = "https://10.10.1.11:1080"
ftp_proxy = "ftp://10.10.1.10:3128"
proxyDict = {
"http" : http_proxy,
"https" : https_proxy,
"ftp" : ftp_proxy
}
page = requests.get(url, headers=headers)
print(page.status_code)
soup = BeautifulSoup(page.content, "lxml")
#print(soup.prettify())
title = soup.find(id = "productTitle")
if title:
title = title.get_text()
else:
title = "default_title"
print(title)

Scrape table fields from html with specific class

So I want to build a simple scraper for google shopping and I encountered some problems.
This is the html text from my request(to https://www.google.es/shopping/product/7541391777504770249/online) where I'm trying to query the highlighted div class sh-osd__total-price inside the div class sh-osd__offer-row :
My code is currently:
from bs4 import BeautifulSoup
from requests import get
url = 'https://www.google.es/shopping/product/7541391777504770249/online'
response = get(url)
html_soup = BeautifulSoup(response.text, 'html.parser')
r = html_soup.findAll('tr', {'class': 'sh-osd__offer-row'}) #Returns empty
print(r)
r = html_soup.findAll('tr', {'class': 'sh-osd__total-price'}) #Returns empty
print(r)
Where both r are empty, beatiful soup doesn't find anything.
Is there any way to find these two div classes with beautiful soup?
You need to add user agent into the headers:
from bs4 import BeautifulSoup
from requests import get
url = 'https://www.google.es/shopping/product/7541391777504770249/online'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'} #<-- added line
response = get(url, headers=headers) #<--- include here
html_soup = BeautifulSoup(response.text, 'html.parser')
r = html_soup.find_all('tr', {'class': 'sh-osd__offer-row'}) #Returns empty
print(r)
r = html_soup.findAll('tr', {'class': 'sh-osd__total-price'}) #Returns empty
print(r)
But, since it's a <table> tag, you can use pandas (it uses beautifulsoup under the hood), but does the hard work for you. It will return a list of all elements that are <table>s as dataframes
import pandas as pd
url = 'https://www.google.es/shopping/product/7541391777504770249/online'
dfs = pd.read_html(url)
print(dfs[-1])
Output:
print(dfs[-1])
Sellers Seller Rating ... Base Price Total Price
0 One Fragance No rating ... £30.95 +£8.76 delivery £39.71
1 eBay No rating ... £46.81 £46.81
2 Carethy.co.uk No rating ... £34.46 +£3.99 delivery £38.45
3 fruugo.co.uk No rating ... £36.95 +£9.30 delivery £46.25
4 cosmeticsmegastore.com/gb No rating ... £36.95 +£9.30 delivery £46.25
5 Perfumes Club UK No rating ... £30.39 +£5.99 delivery £36.38
[6 rows x 5 columns]

Beautifulsoup parsing error

I am trying to extract some information about an App on Google Play and BeautifulSoup doesn't seem to work.
The link is this(say):
https://play.google.com/store/apps/details?id=com.cimaxapp.weirdfacts
My code:
url = "https://play.google.com/store/apps/details?id=com.cimaxapp.weirdfacts"
r = requests.get(url)
html = r.content
soup = BeautifulSoup(html)
l = soup.find_all("div", { "class" : "document-subtitles"})
print len(l)
0 #How is this 0?! There is clearly a div with that class
I decided to go all in, didn't work either:
i = soup.select('html body.no-focus-outline.sidebar-visible.user-has-no-subscription div#wrapper.wrapper.wrapper-with-footer div#body-content.body-content div.outer-container div.inner-container div.main-content div div.details-wrapper.apps.square-cover.id-track-partial-impression.id-deep-link-item div.details-info div.info-container div.info-box-top')
print i
What am I doing wrong?
You need to pretend to be a real browser by supplying the User-Agent header:
import requests
from bs4 import BeautifulSoup
url = "https://play.google.com/store/apps/details?id=com.cimaxapp.weirdfacts"
r = requests.get(url, headers={
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36"
})
html = r.content
soup = BeautifulSoup(html, "html.parser")
title = soup.find(class_="id-app-title").get_text()
rating = soup.select_one(".document-subtitle .star-rating-non-editable-container")["aria-label"].strip()
print(title)
print(rating)
Prints the title and the current rating:
Weird Facts
Rated 4.3 stars out of five stars
To get the additional information field values, you can use the following generic function:
def get_info(soup, text):
return soup.find("div", class_="title", text=lambda t: t and t.strip() == text).\
find_next_sibling("div", class_="content").get_text(strip=True)
Then, if you do:
print(get_info(soup, "Size"))
print(get_info(soup, "Developer"))
You will see printed:
1.4M
Email email#here.com

Categories