i am trying to scrape news from reuters but there is a click to view more at the bottom on the website. I could not know how to load the hidden results by using beautiful soup.
from bs4 import BeautifulSoup
import urllib.request
def scrape_reuters_news(ticker):
url = "https://www.reuters.com/search/news?sortBy=relevance&dateRange=pastWeek&blob="+ticker
scraped_data = urllib.request.urlopen(url)
scraped_data = scraped_data.read()
parsed_articles = BeautifulSoup(scraped_data, 'lxml')
links = parsed_articles.find_all("h3")
articles = []
titles = []
title_class = "Text__text___3eVx1j Text__dark-grey___AS2I_p Text__medium___1ocDap Text__heading_2___sUlNJP Heading__base___1dDlXY Heading__heading_2___3f_bIW ArticleHeader__heading___3ibi0Q"
for link in links:
paragraphs = ""
url = "https://www.reuters.com/"+str(link)[41:63]
scraped_data = urllib.request.urlopen(url)
scraped_data = scraped_data.read()
parsed_article = BeautifulSoup(scraped_data, 'lxml')
article = parsed_article.find_all("p")
title = parsed_article.select("h1", {"class": title_class})
titles.append(title[0].text.strip())
for paragraph in article:
paragraphs += paragraph.text + " "
articles.append(paragraphs)
return titles, articles
# edit
ticker = "apple"
news = scrape_reuters_news(ticker)
When you click the load more a callback is issued that you can find in the network tab. If you grab the number of results from the search page, you can add this into the callback to get all results in one go. I then use regex to extract the id to reconstruct each detail page url and the title (headline)
You would then visit each link to get the paragraph info.
Please note:
There is some de-duplication work to do. There exist different ids which lead to same content. So perhaps exclude based on title?
You may need to consider whether any pre-processing of ticker needs to happen e.g. convert to lowercase, replace spaces with "-". I don't know all your use cases.
from bs4 import BeautifulSoup as bs
import requests, re
ticker = 'apple'
with requests.Session() as s:
r = s.get(f'https://www.reuters.com/search/news?sortBy=relevance&dateRange=pastWeek&blob={ticker}')
soup = bs(r.content, 'lxml')
num_results = soup.select_one('.search-result-count-num').text
r = s.get(f'https://www.reuters.com/assets/searchArticleLoadMoreJson?blob={ticker}&bigOrSmall=big&articleWithBlog=true&sortBy=relevance&dateRange=pastWeek&numResultsToShow={num_results}&pn=&callback=addMoreNewsResults')
p = re.compile(r'id: "(.*?)"')
p2 = re.compile(r'headline: "(.*?)"')
links = [f'https://www.reuters.com/article/id{i}' for i in p.findall(r.text)]
headlines = [bs(i, 'lxml').get_text() for i in p2.findall(r.text)]
print(len(links), len(headlines))
From the detail pages you can get the paragraphs with
paras = ' '.join([i.get_text() for i in soup.select('[data-testid*=paragraph-]')])
I scraped a list of professor contact information from a school website, and now I want to save them individually by name, each name txt file contains their email, tel and office.
ideal outcome
Currently my code is
from bs4 import BeautifulSoup as bs
import requests
url = 'https://www.cb.cityu.edu.hk/is/people/academic.html'
webpage = requests.get(url)
page = bs(webpage.content, 'html.parser')
#define list
name_list = []
phone_list = []
email_list = []
result = page.find_all('div', attrs = {'class': 'staff-details'})
for person in result:
print(person.text)
You can use a loop to fetch the data and simultaneously save the data in a text file.
from bs4 import BeautifulSoup as bs
import requests
url = 'https://www.cb.cityu.edu.hk/is/people/academic.html'
webpage = requests.get(url)
page = bs(webpage.content, 'html.parser')
prof_list = page.select(".staff-details")
for i in prof_list:
name = i.select_one('.name >a').text
email = i.select_one('.list-info div.value:nth-child(2) > a').text
phone = i.select_one('.list-info div.value:nth-child(4)').text
office = i.select_one('.list-info div.value:nth-child(6)').text
with open(name+'.txt', 'w+') as file:
file.write("Email:\n")
file.write(email)
file.write('\nPhone:\n')
file.write(phone)
file.write("\nOffice\n")
file.write(office)
Open file with name you want using context manager in w+ mode
here is a sample code for you
---> Inside Your For Loop
with open(file_name_come_here,"w+") as f :
f.write(content_come_here_as_string)
I'm a beginner with Python & trying to learn with a BeautifulSoup webscraping project.
I'm looking to scrape the record item title, URL of item & purchase date from this URL & export to a CSV.
I made great progress with scraping title & URL but just cannot figure out how to properly code the purchase date info correctly in my for loop (purchase_date variable below).
What's currently happening is the data in the csv file for the purchase date (e.g. p_date title) just displays blank cells with no text.. no error message just no data getting put into csv. Any guidance is much appreciated.
Thank you!!
import requests
from requests import get
from bs4 import BeautifulSoup
import pandas as pd
import numpy as np
headers = {"Accept-Language": "en-US, en;q=0.5"}
url = "https://www.popsike.com/php/quicksearch.php?searchtext=metal+-signed+-promo+-beatles+-zeppelin+-acetate+-test+-sinatra&sortord=aprice&pagenum=1&incldescr=1&sprice=100&eprice=&endfrom=2020&endthru=2020&bidsfrom=&bidsthru=&layout=&flabel=&fcatno="
results = requests.get(url, headers=headers)
soup = BeautifulSoup(results.text, "html.parser")
title = []
date = []
URL = []
record_div = soup.find_all('div', class_='col-md-7 add-desc-box')
for container in record_div:
description = container.a.text
title.append(description)
link = container.find('a')
URL.append(link.get('href'))
purchase_date = container.find('span',class_= 'info-row').text
date.append(purchase_date)
test_data = pd.DataFrame({
'record_description': title,
'link': URL,
'p_date': date
})
test_data['link'] = test_data['link'].str.replace('../','https://www.popsike.com/',1)
print(test_data)
test_data.to_csv('popaaron.csv')
I suggest to change parser type:
soup = BeautifulSoup(results.text, "html5")
And fix search expression for purchase date:
purchase_date = container.select('span.date > b')[0].text.strip(' \t\n\r')
I would need to scrape information regarding Elenco dei comuni per regione on Wikipedia. I would like to create an array that can allow me to associate each comune to the corresponding region, i.e. something like this:
'Abbateggio': 'Pescara' -> Abruzzo
I tried to get information using BeautifulSoup and requests as follows:
from bs4 import BeautifulSoup as bs
import requests
with requests.Session() as s: # use session object for efficiency of tcp re-use
s.headers = {'User-Agent': 'Mozilla/5.0'}
r = s.get('https://it.wikipedia.org/wiki/Comuni_d%27Italia')
soup = bs(r.text, 'html.parser')
for ele in soup.find_all('h3')[:6]:
tx = bs(str(ele),'html.parser').find('span', attrs={'class': "mw-headline"})
if tx is not None:
print(tx['id'])
however it does not work (it returns me an empty list).
The information that I have looked at using Inspect of Google Chrome are the following:
<span class="mw-headline" id="Elenco_dei_comuni_per_regione">Elenco dei comuni per regione</span> (table)
Comuni dell'Abruzzo
(this field should change for each region)
then <table class="wikitable sortable query-tablesortes">
Could you please give me advice on how to get such results?
Any help and suggestion will be appreciated.
EDIT:
Example:
I have a word: comunediabbateggio. This word includes Abbateggio. I would like to know which region can be associated with that city, if it exists.
Information from Wikipedia needs to create a dataset that can allow me to check the field and associate to comuni/cities a region.
What I should expect is:
WORD REGION/STATE
comunediabbateggio Pescara
I hope this can help you. Sorry if it was not clear.
Another example for English speaker that might be slightly better for understanding is the following:
Instead of the Italian link above, you can also consider the following: https://en.wikipedia.org/wiki/List_of_comuni_of_Italy . For each region (Lombardia, Veneto, Sicily, ... ) I would need to collect information about the list of communes of the Provinces.
if you click in a link of List of Communes of ... , there is a table that list the comune, e.g. https://en.wikipedia.org/wiki/List_of_communes_of_the_Province_of_Agrigento.
import re
import requests
from bs4 import BeautifulSoup
import pandas as pd
from tqdm import tqdm
target = "https://en.wikipedia.org/wiki/List_of_comuni_of_Italy"
def main(url):
with requests.Session() as req:
r = req.get(url)
soup = BeautifulSoup(r.content, 'html.parser')
provinces = [item.find_next("span").text for item in soup.findAll(
"span", class_="tocnumber", text=re.compile(r"\d[.]\d"))]
search = [item.replace(
" ", "_") if " " in item else item for item in provinces]
nested = []
for item in search:
for a in soup.findAll("span", id=item):
goes = [b.text.split("of ")[-1]
for b in a.find_next("ul").findAll("a")]
nested.append(goes)
dictionary = dict(zip(provinces, nested))
urls = [f'{url[:24]}{b.get("href")}' for item in search for a in soup.findAll(
"span", id=item) for b in a.find_next("ul").findAll("a")]
return urls, dictionary
def parser():
links, dics = main(target)
com = []
for link in tqdm(links):
try:
df = pd.read_html(link)[0]
com.append(df[df.columns[1]].to_list()[:-1])
except ValueError:
com.append(["N/A"])
com = iter(com)
for x in dics:
b = dics[x]
dics[x] = dict(zip(b, com))
print(dics)
parser()
I am trying to scrape data from the PGA.com website to get a table of all of the golf courses in the United States. In my CSV table I want to include the Name of the golf course ,Address ,Ownership ,Website , Phone number. With this data I would like to geocode it and place into a map and have a local copy on my computer
I utilized Python and Beautiful Soup4 to extract my data. I have reached as far to extract the data and import it into a CSV but I am now having a problem of scraping data from multiple pages on the PGA website. I want to extract ALL THE GOLF COURSES but my script is limited only to one page I want to loop it in away that it will capture all data for golf courses from all pages found in the PGA site. There are about 18000 gold courses and 900 pages to capture data
Attached below is my script. I need help on creating code that will capture ALL data from the PGA website and not just one site but multiple. In this manner it will provide me with all the data of gold courses in the United States.
Here is my script below:
import csv
import requests
from bs4 import BeautifulSoup
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
r = requests.get(url)
soup = BeautifulSoup(r.content)
g_data1=soup.find_all("div",{"class":"views-field-nothing-1"})
g_data2=soup.find_all("div",{"class":"views-field-nothing"})
courses_list=[]
for item in g_data2:
try:
name=item.contents[1].find_all("div",{"class":"views-field-title"})[0].text
except:
name=''
try:
address1=item.contents[1].find_all("div",{"class":"views-field-address"})[0].text
except:
address1=''
try:
address2=item.contents[1].find_all("div",{"class":"views-field-city-state-zip"})[0].text
except:
address2=''
try:
website=item.contents[1].find_all("div",{"class":"views-field-website"})[0].text
except:
website=''
try:
Phonenumber=item.contents[1].find_all("div",{"class":"views-field-work-phone"})[0].text
except:
Phonenumber=''
course=[name,address1,address2,website,Phonenumber]
courses_list.append(course)
with open ('filename5.csv','wb') as file:
writer=csv.writer(file)
for row in courses_list:
writer.writerow(row)
#for item in g_data1:
#try:
#print item.contents[1].find_all("div",{"class":"views-field-counter"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-course-type"})[0].text
#except:
#pass
#for item in g_data2:
#try:
#print item.contents[1].find_all("div",{"class":"views-field-title"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-address"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-city-state-zip"})[0].text
#except:
#pass
This script only captures 20 at a time and I want to capture all in one script which account for 18000 golf courses and 900 pages to scrape form.
The PGA website's search have multiple pages, the url follows the pattern:
http://www.pga.com/golf-courses/search?page=1 # Additional info after page parameter here
this means you can read the content of the page, then change the value of page by 1, and read the the next page.... and so on.
import csv
import requests
from bs4 import BeautifulSoup
for i in range(907): # Number of pages plus one
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(i)
r = requests.get(url)
soup = BeautifulSoup(r.content)
# Your code for each individual page here
if you still read this post , you can try this code too....
from urllib.request import urlopen
from bs4 import BeautifulSoup
file = "Details.csv"
f = open(file, "w")
Headers = "Name,Address,City,Phone,Website\n"
f.write(Headers)
for page in range(1,5):
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(page)
html = urlopen(url)
soup = BeautifulSoup(html,"html.parser")
Title = soup.find_all("div", {"class":"views-field-nothing"})
for i in Title:
try:
name = i.find("div", {"class":"views-field-title"}).get_text()
address = i.find("div", {"class":"views-field-address"}).get_text()
city = i.find("div", {"class":"views-field-city-state-zip"}).get_text()
phone = i.find("div", {"class":"views-field-work-phone"}).get_text()
website = i.find("div", {"class":"views-field-website"}).get_text()
print(name, address, city, phone, website)
f.write("{}".format(name).replace(",","|")+ ",{}".format(address)+ ",{}".format(city).replace(",", " ")+ ",{}".format(phone) + ",{}".format(website) + "\n")
except: AttributeError
f.close()
where it is written range(1,5) just change that with 0,to the last page , and you will get all details in CSV, i tried very hard to get your data in proper format but it's hard:).
You're putting a link to a single page, it's not going to iterate through each one on its own.
Page 1:
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
Page 2:
http://www.pga.com/golf-courses/search?page=1&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0
Page 907:
http://www.pga.com/golf-courses/search?page=906&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0
Since you're running for page 1 you'll only get 20. You'll need to create a loop that'll run through each page.
You can start off by creating a function that does one page then iterate that function.
Right after the search? in the url, starting at page 2, page=1 begins increasing until page 907 where it's page=906.
I noticed that the first solution had a repetition of the first instance, that is because the 0 page and 1 page is the same page. This is resolved by specifying the start page in the range function. Example below...
for i in range(1, 907): #Number of pages plus one
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(i)
r = requests.get(url)
soup = BeautifulSoup(r.content, "html5lib") #Can use whichever parser you prefer
# Your code for each individual page here
Had this same exact problem and the solutions above did not work. I solved mine by accounting for cookies. A requests session helps. Create a session and it'll pull all the pages you need by inserting a cookie to all the numbered pages.
import csv
import requests
from bs4 import BeautifulSoup
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
s = requests.Session()
r = s.get(url)
The PGA website has changed this question has been asked.
It seems they organize all courses by: State > City > Course
In light of this change and the popularity of this question, here's how I'd solve this problem today.
Step 1 - Import everything we'll need:
import time
import random
from gazpacho import Soup # https://github.com/maxhumber/gazpacho
from tqdm import tqdm # to keep track of progress
Step 2 - Scrape all the state URL endpoints:
URL = "https://www.pga.com"
def get_state_urls():
soup = Soup.get(URL + "/play")
a_tags = soup.find("ul", {"data-cy": "states"}, mode="first").find("a")
state_urls = [URL + a.attrs['href'] for a in a_tags]
return state_urls
state_urls = get_state_urls()
Step 3 - Write a function to scrape all the city links:
def get_state_cities(state_url):
soup = Soup.get(state_url)
a_tags = soup.find("ul", {"data-cy": "city-list"}).find("a")
state_cities = [URL + a.attrs['href'] for a in a_tags]
return state_cities
state_url = state_urls[0]
city_links = get_state_cities(state_url)
Step 4 - Write a function to scrape all of the courses:
def get_courses(city_link):
soup = Soup.get(city_link)
courses = soup.find("div", {"class": "MuiGrid-root MuiGrid-item MuiGrid-grid-xs-12 MuiGrid-grid-md-6"}, mode="all")
return courses
city_link = city_links[0]
courses = get_courses(city_link)
Step 5 - Write a function to parse all the useful info about a course:
def parse_course(course):
return {
"name": course.find("h5", mode="first").text,
"address": course.find("div", {'class': "jss332"}, mode="first").strip(),
"url": course.find("a", mode="first").attrs["href"]
}
course = courses[0]
parse_course(course)
Step 6 - Loop through everything and save:
all_courses = []
for state_url in tqdm(state_urls):
city_links = get_state_cities(state_url)
time.sleep(random.uniform(1, 10) / 10)
for city_link in city_links:
courses = get_courses(city_link)
time.sleep(random.uniform(1, 10) / 10)
for course in courses:
info = parse_course(course)
all_courses.append(info)