I want to webscrape a few urls. This is what I do:
import numpy as np
import pandas as pd
from bs4 import BeautifulSoup
import requests
url_2021_int = ["https://www.ecb.europa.eu/press/inter/date/2021/html/index_include.en.html","https://www.ecb.europa.eu/press/inter/date/2020/html/index_include.en.html", "https://www.ecb.europa.eu/press/inter/date/2019/html/index_include.en.html", "https://www.ecb.europa.eu/press/inter/date/2018/html/index_include.en.html", "https://www.ecb.europa.eu/press/inter/date/2017/html/index_include.en.html"]
for url in url_2021_int:
req_int = requests.get(url)
soup_int = BeautifulSoup(req_int.text)
titles_int = soup_int.select(".title a")
titles_int=[data.text for data in titles_int]
However, I get data only for the last url (2017).
What am I doing wrong?
Thanks!
When you use req_int = requests.get(url) in the loop, the req_int variable is re-written each time.
If you want to store the requests.get(url) results in a list variable you can use
req_ints = [requests.get(url) for url in url_2021_int]
However, it seems logical to process the data in the same loop:
for url in url_2021_int:
req_int = requests.get(url)
soup_int = BeautifulSoup(req_int.text, "html.parser")
titles_int = soup_int.select(".title a")
titles_int=[data.text for data in titles_int]
Note that you can specify the "html.parser" as a second argument to the BeautifulSoup call, since the documents you are parsing are HTML documents.
Related
Wondering if you could help please. Python newbie here.
I am crawling multiple urls in the one script, but it's returning 3 dataframes. One for each iteration.
What I am looking to achieve is one single dataframe that contains the URLs from each iteration.
What I have so far is the following:
import requests
from bs4 import BeautifulSoup
import pandas as pd
def get_links(url):
links = []
website = requests.get(url)
website_text = website.text
soup = BeautifulSoup(website_text)
for link in soup.find_all('a'):
links.append(link.get('href'))
data = (link in links)
df = pd.DataFrame(links)
display(df)
get_links('https://www.example.com/')
get_links('https://www.example2.com/')
get_links('https://www.example3.com/')
Thank you for your help
you should let the function return the dataframe instead of only display it
and then you should combine the outputs like that
https://pandas.pydata.org/docs/reference/api/pandas.concat.html
df = pd.concat([df1,df2,df3])
from bs4 import BeautifulSoup, SoupStrainer
import requests
# Reason Behind using `SoupStrainer` is to increase performance to parse only `a` tags.
# https://www.crummy.com/software/BeautifulSoup/bs4/doc/#soupstrainer
urls = ['Link1', 'Link2', 'Link3']
def get_links():
for url in urls:
r = requests.get(url)
links = BeautifulSoup(r.text, 'lxml', parse_only=SoupStrainer('a'))
for link in links:
print(link.get('href', 'N/A'))
get_links()
I have setup BeautifulSoup to find a specific class for two webpages.
I would like to know how to write each URL's result to a unique cell in one CSV?
Also is there a limit to the number of URLs I can read as I would like to expand this to about 200 URLs once I get this working.
The class is always the same and I don't need any formatting just the raw HTML in one cell per URL.
Thanks for any ideas.
from bs4 import BeautifulSoup
import requests
urls = ['https://www.ozbargain.com.au/','https://www.ozbargain.com.au/forum']
for u in urls:
response = requests.get(u)
data = response.text
soup = BeautifulSoup(data,'lxml')
soup.find('div', class_="block")
Use pandas to work with tabular data: pd.DataFrame to create a table, and pd.to_csv to save table as csv (might also check out the documentation, append mode for example).
Basically it.
import requests
import pandas as pd
from bs4 import BeautifulSoup
def func(urls):
for url in urls:
data = requests.get(url).text
soup = BeautifulSoup(data,'lxml')
yield {
"url": url, "raw_html": soup.find('div', class_="block")
}
urls = ['https://www.ozbargain.com.au/','https://www.ozbargain.com.au/forum']
data = func(urls)
table = pd.DataFrame(data)
table.to_csv("output.csv", index=False)
I am attempting to extract campaign_hearts and postal_code from the code in the script tag here (the entire code is too long to post):
<script>
...
"campaign_hearts":4817,"social_share_total":11242,"social_share_last_update":"2020-01-17T10:51:22-06:00","location":{"city":"Los Angeles, CA","country":"US","postal_code":"90012"},"is_partner":false,"partner":{},"is_team":true,"team":{"name":"Team STEVENS NATION","team_pic_url":"https://d2g8igdw686xgo.cloudfront.net
...
I can identify the script I need with the following code:
from bs4 import BeautifulSoup
import numpy as np
import pandas as pd
from time import sleep
import requests
import re
import json
page = requests.get("https://www.gofundme.com/f/eric-stevens-care-trust")
soup = BeautifulSoup(page.content, 'html.parser')
all_scripts = soup.find_all('script')
all_scripts[0]
However, I'm at a loss for how to extract the values I want. (I'm very new to Python.)
This thread recommended the following solution for a similar problem (edited to reflect the html I'm working with).
data = json.loads(all_scripts[0].get_text()[27:])
However, running this produces an error: JSONDecodeError: Expecting value: line 1 column 1 (char 0).
What can I do to extract the values I need now that I have the correct script identified? I have also tried the solutions listed here, but had trouble importing Parser.
You can parse the content of <script> with json module and then get your values. For example:
import re
import json
import requests
url = 'https://www.gofundme.com/f/eric-stevens-care-trust'
txt = requests.get(url).text
data = json.loads(re.findall(r'window\.initialState = ({.*?});', txt)[0])
# print( json.dumps(data, indent=4) ) # <-- uncomment this to see all data
print('Campaign Hearts =', data['feed']['campaign']['campaign_hearts'])
print('Postal Code =', data['feed']['campaign']['location']['postal_code'])
Prints:
Campaign Hearts = 4817
Postal Code = 90012
The more libraries you use; the more inefficient a code becomes! Here is a simpler solution-
#This imports the website content.
import requests
url = "https://www.gofundme.com/f/eric-stevens-care-trust"
a = requests.post(url)
a= (a.content)
print(a)
#These will show your data.
campaign_hearts = str(a,'utf-8').split('campaign_hearts":')[1]
campaign_hearts = campaign_hearts.split(',"social_share_total"')[0]
print(campaign_hearts)
postal_code = str(a,'utf-8').split('postal_code":"')[1]
postal_code = postal_code.split('"},"is_partner')[0]
print(postal_code)
Your json.loads was failing because of the final semicolon. It will work if you use a regex to extract only the object string (excluding the final semicolon).
from bs4 import BeautifulSoup
import numpy as np
import pandas as pd
from time import sleep
import requests
import re
import json
page = requests.get("https://www.gofundme.com/f/eric-stevens-care-trust")
soup = BeautifulSoup(page.content, 'html.parser')
all_scripts = soup.find_all('script')
txt = all_scripts[0].get_text()
data = json.loads(re.findall(r'window\.initialState = ({.*?});', txt)[0])
This should be fine for now, I might try to write a pure lxml version or at least improve the searching for the element.
This solution uses regex to get only the JSON data, without the window.initialState = and semicolon.
import json
import re
import requests
from bs4 import BeautifulSoup
url_1 = "https://www.gofundme.com/f/eric-stevens-care-trust"
req = requests.get(url_1)
soup = BeautifulSoup(req.content, 'lxml')
script_tag = soup.find('script')
raw_json = re.fullmatch(r"window\.initialState = (.+);", script_tag.text).group(1)
json_content = json.loads(raw_json)
I am trying to scrape a page website/post-sitemap.xml which contains all url's posted for a wordpress website. In the first step, I need to make a list of all the url's present in post-sitemap. When I use requests.get and I check the output, it opens all of the internal urls as well, which is weird. My intention is to make a list of all url's first and then using a loop, I will scrape individual url's in the next function. Below is the code I have done so far. I would need all url's as a list as my final output if python gurus can help.
I have tried using requests.get and openurl but nothing seems to open only the base url for /post-sitemap.xml
import pandas as pd
import numpy as np
from urllib.request import urlopen
from bs4 import BeautifulSoup
import requests
import re
class wordpress_ext_url_cleanup(object):
def __init__(self,wp_url):
self.wp_url_raw = wp_url
self.wp_url = wp_url + '/post-sitemap.xml/'
def identify_ext_url(self):
html = requests.get(self.wp_url)
print(self.wp_url)
print(html.text)
soup = BeautifulSoup(html.text,'lxml')
#print(soup.get_text())
raw_data = soup.find_all('tr')
print (raw_data)
#for link in raw_data:
#print(link.get("href"))
def main():
print ("Inside Main Function");
url="http://punefirst dot com" #(knowingly removed the . so it doesnt look spammy)
first_call = wordpress_ext_url_cleanup(url)
first_call.identify_ext_url()
if __name__ == '__main__':
main()
I would need all 548 url's present in the post sitemap as a list which I will use it for the next function for further scraping.
The document that is returned from the server is XML and transformed with XSLT to HTML form (more info here). To parse all links from this XML, you can use this script:
import requests
from bs4 import BeautifulSoup
url = 'http://punefirst.com/post-sitemap.xml/'
soup = BeautifulSoup(requests.get(url).text, 'lxml')
for loc in soup.select('url > loc'):
print(loc.text)
Prints:
http://punefirst.com
http://punefirst.com/hospitals/pcmc-hospitals/aditya-birla-memorial-hospital-chinchwad-pune
http://punefirst.com/hospitals/pcmc-hospitals/saijyoti-hospital-and-icu-chinchwad-pune
http://punefirst.com/hospitals/pcmc-hospitals/niramaya-hospital-chinchwad-pune
http://punefirst.com/hospitals/pcmc-hospitals/chetna-hospital-chinchwad-pune
http://punefirst.com/hospitals/hadapsar-hospitals/pbmas-h-v-desai-eye-hospital
http://punefirst.com/hospitals/punecentral-hospitals/shree-sai-prasad-hospital
http://punefirst.com/hospitals/punecentral-hospitals/sadhu-vaswani-missions-medical-complex
http://punefirst.com/hospitals/katraj-kondhwa-hospitals/shivneri-hospital
http://punefirst.com/hospitals/punecentral-hospitals/kelkar-nursing-home
http://punefirst.com/hospitals/pcmc-hospitals/shrinam-hospital
http://punefirst.com/hospitals/pcmc-hospitals/dhanwantari-hospital-nigdi
http://punefirst.com/hospitals/punecentral-hospitals/dr-tarabai-limaye-hospital
http://punefirst.com/hospitals/katraj-kondhwa-hospitals/satyanand-hospital-kondhwa-pune
...and so on.
I need to do some real estate market research and for this in need the prices, and other values from new houses.
So my idea was to go on the website where i get the information.
Go to the Main-Search-Site and scrape all the RealEstateIDs that would navigate me directly to the single pages for each house where i can than extract my infos that i need.
My problem is how do i get all the real estate ids from the main page and store them in a list, so i can use them in the next step to build the urls with them to go to the acutal sites.
I tried it with beautifulsoup but failed because i dont understand how to search for a specific word and extract what comes after it.
The html code looks like this:
""realEstateId":110356727,"newHomeBuilder":"false","disabledGrouping":"false","resultlist.realEstate":{"#xsi.type":"search:ApartmentBuy","#id":"110356727","title":"
Since the value "realEstateId" appears around 60 times, i want to scrape evertime the number (here: 110356727) that comes after it and store it in a list, so that i can use them later.
Edit:
import time
import urllib.request
from urllib.request import urlopen
import bs4 as bs
import datetime as dt
import matplotlib.pyplot as plt
from matplotlib import style
import numpy as np
import os
import pandas as pd
import pandas_datareader.data as web
import pickle
import requests
from requests import get
url = 'https://www.immobilienscout24.de/Suche/S-T/Wohnung-Kauf/Nordrhein-Westfalen/Duesseldorf/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/true?enteredFrom=result_list'
response = get(url)
from bs4 import BeautifulSoup
html_soup = BeautifulSoup(response.text, 'html.parser')
type(html_soup)
def expose_IDs():
resp = requests.get('https://www.immobilienscout24.de/Suche/S-T/Wohnung-Kauf/Nordrhein-Westfalen/Duesseldorf/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/true?enteredFrom=result_list')
soup = bs.BeautifulSoup(resp.text, 'lxml')
table = soup.find('resultListModel')
tickers = []
for row in table.findAll('realestateID')[1:]:
ticker = row.findAll(',')[0].text
tickers.append(ticker)
with open("exposeID.pickle", "wb") as f:
pickle.dump(tickers, f)
return tickers
expose_IDs()
Something like this? There are 68 keys in a dictionary that are ids. I use regex to grab the same script as you are after and trim of an unwanted character, then load with json.loads and access the json object as shown in image at bottom.
import requests
import json
from bs4 import BeautifulSoup as bs
import re
res = requests.get('https://www.immobilienscout24.de/Suche/S-T/Wohnung-Kauf/Nordrhein-Westfalen/Duesseldorf/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/true?enteredFrom=result_list')
soup = bs(res.content, 'lxml')
r = re.compile(r'resultListModel:(.*)')
data = soup.find('script', text=r).text
script = r.findall(data)[0].rstrip(',')
#resultListModel:
results = json.loads(script)
ids = list(results['searchResponseModel']['entryInformation'].keys())
print(ids)
Ids:
Since website updated:
import requests
import json
from bs4 import BeautifulSoup as bs
import re
res = requests.get('https://www.immobilienscout24.de/Suche/S-T/Wohnung-Kauf/Nordrhein-Westfalen/Duesseldorf/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/-/true?enteredFrom=result_list')
soup = bs(res.content, 'lxml')
r = re.compile(r'resultListModel:(.*)')
data = soup.find('script', text=r).text
script = r.findall(data)[0].rstrip(',')
results = json.loads(script)
ids = [item['#id'] for item in results['searchResponseModel']['resultlist.resultlist']['resultlistEntries'][0]['resultlistEntry']]
print(ids)