Extract and Format Site Data Python - python

This is for Python 3.5.x
What I'm looking for is to find the header, after a peice of the HTML code being
<h3 class = "title-link__title"><span class="title=link__text">News Here</span>
with urllib.request.urlopen('http://www.bbc.co.uk/news') as r:
HTML = r.read()
HTML = list(HTML)
for i in range(len(HTML)):
HTML[i] = chr(HTML[i])
How can I get it so I extract just the header as that's all I need. I'll try and help for detail in anyway i can.

Fetching information from webpages is called web scraping.
One of the best tools to do this job is the BeautifulSoup library.
from bs4 import BeautifulSoup
import urllib
#opening page
r = urllib.urlopen('http://www.bbc.co.uk/news').read()
#creating soup
soup = BeautifulSoup(r)
#useful for understanding the layout of your page info
#print soup.prettify()
#creating a ResultSet with all h3 tags that contains a class named 'title-link__title'
a = soup.findAll("h3", {"class":"title-link__title"})
#counting ocurrences
len(a)
#result = 44
#get text of first header
a[0].text
#result = u'\nMay v Leadsom to be next UK PM\n'
#get text of second header
a[1].text
#result = u'\nVideo shows US police shooting aftermath\n'

Related

How to scrape the text within a div if there's multiple divs with the same class name

I am trying to get the amount of chapters in this manga using BeautifulSoup but the way it's contained is making it confusing:
[The Section]https://gyazo.com/c45fef82b0ce52dacd99d213538ab570)
I only want the Chapter number and not the content of the other divs. Currently I have (not the full code):
[The Website]https://www.anime-planet.com/manga/the-beginning-after-the-end
chp = []
temp = soup.select('section.pure-g entryBar > div.pure-1 md-1-5')
for txt in temp:
if "Ch" in txt.text:
chp.append(txt.text)
How would I access the text within the first div?
Looking at the structure of HTML, you can extract text from the first <div> under class="entryBar":
import requests
from bs4 import BeautifulSoup
url = "https://www.anime-planet.com/manga/the-beginning-after-the-end"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
ch = soup.select_one(".entryBar > div").text.split()[-1].strip("+")
print(ch)
Prints:
159

how to scrape data on a website with view more with beautifulsoup

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-]')])

How to scrape data from interactive chart using python?

I have a next link which represent an exact graph I want to scrape: https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1
I'm simply can't understand is it a xml or svg graph and how to scrape data. I think I need to use bs4, requests but don't know the way to do that.
Anyone could help?
You will load HTML like this:
import requests
url = "https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
resp = requests.get(url)
data = resp.text
Then you will create a BeatifulSoup object with this HTML.
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, features="html.parser")
After this, it is usually very subjective how to parse out what you want. The candidate codes may vary a lot. This is how I did it:
Using BeautifulSoup, I parsed all "rect"s and check if "onmouseover" exists in that rect.
rects = soup.svg.find_all("rect")
yx_points = []
for rect in rects:
if rect.has_attr("onmouseover"):
text = rect["onmouseover"]
x_start_index = text.index("'") + 1
y_finish_index = text[x_start_index:].index("'") + x_start_index
yx = text[x_start_index:y_finish_index].split()
print(text[x_start_index:y_finish_index])
yx_points.append(yx)
As you can see from the image below, I scraped onmouseover= part and get those 02.2015 155,1 parts.
Here, this is how yx_points looks like now:
[['12.2009', '100,0'], ['01.2010', '101,8'], ['02.2010', '103,7'], ...]
from bs4 import BeautifulSoup
import requests
import re
#First get all the text from the url.
url="https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
response = requests.get(url)
html = response.text
#Find all the tags in which the data is stored.
soup = BeautifulSoup(html, 'lxml')
texts = soup.findAll("rect")
final = []
for each in texts:
names = each.get('onmouseover')
try:
q = re.findall(r"'(.*?)'", names)
final.append(q[0])
except Exception as e:
print(e)
#The details are appended to the final variable

python crawling beautifulsoup how to crawl several pages?

Please Help.
I want to get all the company names of each pages and they have 12 pages.
http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/1
http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/2
-- this website only changes the number.
So Here is my code so far.
Can I get just the title (company name) of 12 pages?
Thank you in advance.
from bs4 import BeautifulSoup
import requests
maximum = 0
page = 1
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/1'
response = requests.get(URL)
source = response.text
soup = BeautifulSoup(source, 'html.parser')
whole_source = ""
for page_number in range(1, maximum+1):
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/' + str(page_number)
response = requests.get(URL)
whole_source = whole_source + response.text
soup = BeautifulSoup(whole_source, 'html.parser')
find_company = soup.select("#content > div.wrap_analysis_data > div.public_con_box.public_list_wrap > ul > li:nth-child(13) > div > strong")
for company in find_company:
print(company.text)
---------Output of one page
---------page source :)
So, you want to remove all the headers and get only the string of the company name?
Basically, you can use the soup.findAll to find the list of company in the format like this:
<strong class="company"><span>중소기업진흥공단</span></strong>
Then you use the .find function to extract information from the <span> tag:
<span>중소기업진흥공단</span>
After that, you use .contents function to get the string from the <span> tag:
'중소기업진흥공단'
So you write a loop to do the same for each page, and make a list called company_list to store the results from each page and append them together.
Here's the code:
from bs4 import BeautifulSoup
import requests
maximum = 12
company_list = [] # List for result storing
for page_number in range(1, maximum+1):
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/{}'.format(page_number)
response = requests.get(URL)
print(page_number)
whole_source = response.text
soup = BeautifulSoup(whole_source, 'html.parser')
for entry in soup.findAll('strong', attrs={'class': 'company'}): # Finding all company names in the page
company_list.append(entry.find('span').contents[0]) # Extracting name from the result
The company_list will give you all the company names you want
I figured it out eventually. Thank you for your answer though!
image : code captured in jupyter notebook
Here is my final code.
from urllib.request import urlopen
from bs4 import BeautifulSoup
company_list=[]
for n in range(12):
url = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/{}'.format(n+1)
webpage = urlopen(url)
source = BeautifulSoup(webpage,'html.parser',from_encoding='utf-8')
companys = source.findAll('strong',{'class':'company'})
for company in companys:
company_list.append(company.get_text().strip().replace('\n','').replace('\t','').replace('\r',''))
file = open('company_name1.txt','w',encoding='utf-8')
for company in company_list:
file.write(company+'\n')
file.close()

How can I loop scraping data for multiple pages in a website using python and beautifulsoup4

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)

Categories