I took an introductory course in Python this semester and am now trying to do a project. However, I don't really know what code I should write to create multiple .txt files of which the title will be different for each file.
I scraped all the terms and definitions from the website http://www.hogwartsishere.com/library/book/99/. Title of the .txt file should for example be 'Aconite.txt' and the content of the file should be the title and the definition. Every term with its definition can be found in a separate p-tag and the term itself is a b-tag withing the p-tag. Can I use this to write my code?
I suppose I will need to use a for-loop for this, but I don't really know where to start. I searched StackOverflow and found several solutions, but all of them contain code I am not familiar with and/or relate to another issue.
This is what I have so far:
#!/usr/bin/env/ python
import requests
import bs4
def download(url):
r = requests.get(url)
html = r.text
soup = bs4.BeautifulSoup(html, 'html.parser')
terms_definition = []
#for item in soup.find_all('p'): #beter definiëren
items = soup.find_all("div", {"class" : "font-size-16 roboto"})
for item in items:
terms = item.find_all("p")
for term in terms:
#print(term)
if term.text is not 'None':
#print(term.text)
#print("\n")
term_split = term.text.split()
print(term_split)
if term.text != None and len(term.text) > 1:
if '-' in term.text.split():
print(term.text)
print('\n')
if item.find('p'):
terms_definition.append(item['p'])
print(terms_definition)
return terms_definition
def create_url(start, end):
list_url = []
base_url = 'http://www.hogwartsishere.com/library/book/99/chapter/'
for x in range(start, end):
list_url.append(base_url + str(x))
return list_url
def search_all_url(list_url):
for url in list_url:
download(url)
#write data into separate text files. Word in front of the dash should be title of the document, term and definition should be content of the text file
#all terms and definitions are in separate p-tags, title is a b-tag within the p-tag
def name_term
def text_files
path_write = os.path.join('data', name_term +'.txt') #'term' should be replaced by the scraped terms
with open(path_write, 'w') as f:
f.write()
#for loop? in front of dash = title / everything before and after dash = text (file content) / empty line = new file
if __name__ == '__main__':
download('http://www.hogwartsishere.com/library/book/99/chapter/1')
#list_url = create_url(1, 27)
#search_all_url(list_url)
Thanks in advance!
You can iterate over all pages (1-27) to get its content, then parse each page with bs4 and then save results to files:
import requests
import bs4
import re
for i in range(1, 27):
r = requests.get('http://www.hogwartsishere.com/library/book/99/chapter/{}/'.format(i)).text
soup = bs4.BeautifulSoup(r, 'html.parser')
items = soup.find_all("div", {"class": "font-size-16 roboto"})
for item in items:
terms = item.find_all("p")
for term in terms:
title = re.match('^(.*) -', term.text).group(1).replace('/', '-')
with open(title + '.txt', 'w', encoding='utf-8') as f:
f.write(term.text)
Output files:
Hi Wrote a web scraping program and it gets the ASN number correctly, but after all the data is scraped, it returns a error "Array Out if Bounds".
I am using Pycharm and latest python version. Below is my code.
There is already a similar issue on stackoverflow but I am not able to get the pieces together and make it work. (Web Scraping List Index Out Of Range) its the exact same error but I am not sure how to get it working for my List.
Error seems to be at current_country = link.split('/')[2]
Any help is appreciated. Thank you.
import urllib.request
import bs4
import re
import json
url = 'https://ipinfo.io/countries'
SITE = 'https://ipinfo.io'
def url_to_soup(url):
req = urllib.request.Request(url)
opener = urllib.request.build_opener()
html = opener.open(req)
soup = bs4.BeautifulSoup(html, "html.parser")
return soup
def find_pages(page):
pages = []
for link in page.find_all(href=re.compile('/countries')):
pages.append(link.get('href'))
return pages
def scrape_pages(links):
mappings = {}
print("Scraping Pages for ASN Data...")
for link in links:
country_page = url_to_soup(SITE + link)
current_country = link.split('/')[2]
print(current_country)
for row in country_page.find_all('tr'):
columns = row.find_all('td')
if len(columns) > 0:
current_asn = re.findall(r'\d+', columns[0].string)[0]
print(current_asn)
"""
name = columns[1].string
routes_v4 = columns[3].string
routes_v6 = columns[5].string
mappings[current_asn] = {'Country': current_country,
'Name': name,
'Routes v4': routes_v4,
'Routes v6': routes_v6}
return mappings """
main_page = url_to_soup(url)
country_links = find_pages(main_page)
#print(country_links)
asn_mappings = scrape_pages(country_links)
print(asn_mappings)
The last href contains string "/countries" in https://ipinfo.io/countries is actually "/countries":
<li>Global ASNs</li>
After splitting this link, it produced list ["", "countries"] where the third element was missing. To fix this problem, simply check the list length before retrieving the third element:
...
current_country = link.split('/')
if len(current_country) < 3:
continue
current_country = current_country[2]
...
Another solution is to exclude the last href by changing the regexp to:
...
for link in page.find_all(href=re.compile('/countries/')):
...
Im trying to open the links that contain certain words on that page. And if the words are present on that page such as "engineering" then return the link if not pass.
here is what I have so far: The inputs I put are engineering and location is north york
import requests
from bs4 import BeautifulSoup
import webbrowser
import time
jobsearch = input("What type of job?: ")
location = input("What is your location: ")
url = ("https://ca.indeed.com/jobs?q=" + jobsearch + "&l=" + location)
base_url = 'https://ca.indeed.com/'
r = requests.get(url)
rcontent = r.content
prettify = BeautifulSoup(rcontent, "html.parser")
filter_words = ['chemical engineering', 'instrumentation', 'QA']
all_job_url = []
filtered_job_links = []
http_flinks = []
flinks = []
def get_all_joblinks(): # obtains all the links on the search page
for tag in prettify.find_all('a', {'data-tn-element':"jobTitle"}):
link = tag['href']
all_job_url.append(link)
def filter_links():
for eachurl in all_job_url: # iterates through each link
rurl = requests.get(base_url + eachurl)
content = rurl.content
soup = BeautifulSoup(content, "html.parser")
summary = soup.get_text()
#supposed to filter links based on certain words within text on link page
if any(word in summary for word in filter_words):
for filtered_link in soup.find_all('link', {'rel':'canonical'}):
flink = filtered_link['href'] # obtains only filtered links
if "http:" in flink:
http_flinks.append(flink)
print(http_flinks)
else:
flinks.append(flink)
#website = webbrowser.open_new(base_url + flink)
time.sleep(3)
print(flinks)
else:
print("nothing")
pass
def search_job():
while True:
if prettify.select('div.no_results'):
print("no job matches found")
break
else:
# opens the web page of job search if entries are found
website = webbrowser.open_new(url)
break
get_all_joblinks()
filter_links()
continuing on previous work to crawl all news result about query and to return title and url, I am refining the crawler to get all results from all pages in Google News. Current code seems can only return the 1st page Googel news search result. Would be grateful to know how to get all pages results. Many thanks!
my codes below:
import requests
from bs4 import BeautifulSoup
import time
import datetime
from random import randint
import numpy as np
import pandas as pd
query2Google = input("What do you want from Google News?\n")
def QGN(query2Google):
s = '"'+query2Google+'"' #Keywords for query
s = s.replace(" ","+")
date = str(datetime.datetime.now().date()) #timestamp
filename =query2Google+"_"+date+"_"+'SearchNews.csv' #csv filename
f = open(filename,"wb")
url = "http://www.google.com.sg/search?q="+s+"&tbm=nws&tbs=qdr:y" # URL for query of news results within one year and sort by date
#htmlpage = urllib2.urlopen(url).read()
time.sleep(randint(0, 2))#waiting
htmlpage = requests.get(url)
print("Status code: "+ str(htmlpage.status_code))
soup = BeautifulSoup(htmlpage.text,'lxml')
df = []
for result_table in soup.findAll("div", {"class": "g"}):
a_click = result_table.find("a")
#print ("-----Title----\n" + str(a_click.renderContents()))#Title
#print ("----URL----\n" + str(a_click.get("href"))) #URL
#print ("----Brief----\n" + str(result_table.find("div", {"class": "st"}).renderContents()))#Brief
#print ("Done")
df=np.append(df,[str(a_click.renderContents()).strip("b'"),str(a_click.get("href")).strip('/url?q='),str(result_table.find("div", {"class": "st"}).renderContents()).strip("b'")])
df = np.reshape(df,(-1,3))
df1 = pd.DataFrame(df,columns=['Title','URL','Brief'])
print("Search Crawl Done!")
df1.to_csv(filename, index=False,encoding='utf-8')
f.close()
return
QGN(query2Google)
There used to be an ajax api, but it's no longer avaliable .
Still , you can modify your script with a for loop if you want to get a number of pages , or a while loop if you want to get all pages .
Example :
url = "http://www.google.com.sg/search?q="+s+"&tbm=nws&tbs=qdr:y&start="
pages = 10 # the number of pages you want to crawl #
for next in range(0, pages*10, 10) :
page = url + str(next)
time.sleep(randint(1, 5)) # you may need longer than that #
htmlpage = requests.get(page) # you should add User-Agent and Referer #
print("Status code: " + str(htmlpage.status_code))
if htmlpage.status_code != 200 :
break # something went wrong #
soup = BeautifulSoup(htmlpage.text, 'lxml')
... process response here ...
next_page = soup.find('td', { 'class':'b', 'style':'text-align:left' })
if next_page is None or next_page.a is None :
break # there are no more pages #
Keep in mind that google doesn't like bots , you might get a ban .
You could add 'User-Agent' and 'Referer' in headers to simulate a web browser , and use time.sleep(random.uniform(2, 6)) to simulate a human ... or use selenium.
You can also add &num=25 to the end of your query and you'll get back a webpage with that number of results. In this example youll get back 25 google results back.
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)