I got this project where I'm scraping data on Trulia.com and where I want to get the max number of page (last number) for a specific location (photo below) so I can loop through it and get all the hrefs.
To get that last number, I have my code that run as planned and should return an integer but it doesn't always return the same number. I added the print(comprehension list) to understand what's wrong. Here is the code and the output below. The return is commented but sould return the last number of the output list as an int.
city_link = "https://www.trulia.com/for_rent/San_Francisco,CA/"
def bsoup(url):
resp = r.get(url, headers=req_headers)
soup = bs(resp.content, 'html.parser')
return soup
def max_page(link):
soup = bsoup(link)
page_num = soup.find_all(attrs={"data-testid":"pagination-page-link"})
print([x.get_text() for x in page_num])
# return int(page_num[-1].get_text())
for x in range(10):
max_page(city_link)
I have no clue why sometimes it's returning something wrong. The photo above is the corresponding link.
Okay, now if I understand what you want, you are trying to see how many pages of links there are for a given location for rent. If we can assume the given link is the only required link, this code:
import requests
import bs4
url = "https://www.trulia.com/for_rent/San_Francisco,CA/"
req = requests.get(url)
soup = bs4.BeautifulSoup(req.content, features='lxml')
def get_number_of_pages(soup):
caption_tag = soup.find('div', class_="Text__TextBase-sc-1cait9d-0-
div Text__TextContainerBase-sc-1cait9d-1 RBSGf")
pagination = caption_tag.text
words = pagination.split(" ")
values = []
for word in words:
if not word.isalpha():
values.append(word)
links_per_page = values[0].split('-')[1]
total_links = values[1].replace(',', '')
no_of_pages = round(int(total_links)/int(links_per_page) + 0.5)
return no_of_pages
for i in range(10):
print(get_number_of_pages(soup))
achieves what you're looking for, and has repeatability because it doesn't interact with javascript, but the pagination caption at the bottom of the page.
I am trying to pull links from a webpage at a certain position, then open that link, and then repeat that process for the provided number of times. The problem is I keep getting the same URL returned, so it seems like my code is just pulling the tag, printing the tag, not opening it, and doing that process X number of times before closing.
I have written and re-written this code a number of times, but for the life of me I just can't figure it out. Please tell me what I am doing wrong
Tried using list to put anchor tags in, then open the url at the requested position in the list, then do a list clear before starting the loop over again.
import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import ssl
# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
#url = input('Enter - ')
url = "http://py4e-data.dr-chuck.net/known_by_Fikret.html"
html = urllib.request.urlopen(url, context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')
count = 0
url_loop = int(input("Enter how many times to loop through: "))
url_pos= int(input("Enter position of URL: "))
url_pos = url_pos - 1
print(url_pos)
# Retrieve all of the anchor tags
tags = soup('a')
while True:
if url_loop == count:
break
html = urllib.request.urlopen(url, context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')
url = tags[url_pos].get('href', None)
print("Acquiring URL: ", url)
count = count + 1
print("final URL:", url)
it could be that the tags are only extracted once for the initial document:
# Retrieve all of the anchor tags
tags = soup('a')
If you were to re-extract the tags after fetching each document, they would reflect the last document.
I am trying to extract data from website and have following code which is extracting all URLs from Main category and its sub category links.
I am now stuck in saving the extracted output with line separator (to move each URL in separate line) in a file -Medical.tsv
Need help on this.
Code is given below:
from bs4 import BeautifulSoup
import requests
import time
import random
def write_to_file(file,mode, data, newline=None, with_tab=None): #**
with open(file, mode, encoding='utf-8') as l:
if with_tab == True:
data = ''.join(data)
if newline == True:
data = data+'\n'
l.write(data)
def get_soup(url):
return BeautifulSoup(requests.get(url).content, "lxml")
url = 'http://www.medicalexpo.com/'
soup = get_soup(url)
raw_categories = soup.select('div.univers-main li.category-group-item a')
category_links = {}
for cat in (raw_categories):
t0 = time.time()
response_delay = time.time() - t0 # It wait 10x longer than it took them to respond using delay.
time.sleep(10*response_delay) # This way if the site gets overwhelmed and starts to slow down, the code will automatically back off.
time.sleep(random.randint(2,5)) # This will provide random time intervals of 2 and 3 secs acting as human crawl instead of bot.
soup = get_soup(cat['href'])
links = soup.select('#category-group li a')
category_links[cat.text] = [link['href'] for link in links]
print(category_links)
You got the write_to_file function but you never call it? mode have to be w or w+(if you wanna overwrite in the case if the file already exists)
This script is generating a csv with the data from only one of the urls fed into it. There are meant to be 98 sets of results, however the for loop isn't getting past the first url.
I've been working on this for 12hrs+ today, what am I missing in order get the correct results?
import requests
import re
from bs4 import BeautifulSoup
import csv
#Read csv
csvfile = open("gyms4.csv")
csvfilelist = csvfile.read()
def get_page_data(urls):
for url in urls:
r = requests.get(url.strip())
soup = BeautifulSoup(r.text, 'html.parser')
yield soup # N.B. use yield instead of return
print r.text
with open("gyms4.csv") as url_file:
for page in get_page_data(url_file):
name = page.find("span",{"class":"wlt_shortcode_TITLE"}).text
address = page.find("span",{"class":"wlt_shortcode_map_location"}).text
phoneNum = page.find("span",{"class":"wlt_shortcode_phoneNum"}).text
email = page.find("span",{"class":"wlt_shortcode_EMAIL"}).text
th = pages.find('b',text="Category")
td = th.findNext()
for link in td.findAll('a',href=True):
match = re.search(r'http://(\w+).(\w+).(\w+)', link.text)
if match:
web_address = link.text
gyms = [name,address,phoneNum,email,web_address]
gyms.append(gyms)
#Saving specific listing data to csv
with open ("xgyms.csv", "w") as file:
writer = csv.writer(file)
for row in gyms:
writer.writerow([row])
You have 3 for-loops in your code and do not specifiy which one causes problem. I assume it is the one in get_page_date() function.
You leave the looop exactly in the first run with the return assignemt. That is why you never get to the second url.
There are at least two possible solutions:
Append every parsed line of url to a list and return that list.
Move you processing code in the loops and append the parsed data to gyms in the loop.
As Alex.S said, get_page_data() returns on the first iteration, hence subsequent URLs are never accessed. Furthermore, the code that extracts data from the page needs to be executed for each page downloaded, so it needs to be in a loop too. You could turn get_page_data() into a generator and then iterate over the pages like this:
def get_page_data(urls):
for url in urls:
r = requests.get(url.strip())
soup = BeautifulSoup(r.text, 'html.parser')
yield soup # N.B. use yield instead of return
with open("gyms4.csv") as url_file:
for page in get_page_data(url_file):
name = page.find("span",{"class":"wlt_shortcode_TITLE"}).text
address = page.find("span",{"class":"wlt_shortcode_map_location"}).text
phoneNum = page.find("span",{"class":"wlt_shortcode_phoneNum"}).text
email = page.find("span",{"class":"wlt_shortcode_EMAIL"}).text
# etc. etc.
You can write the data to the CSV file as each page is downloaded and processed, or you can accumulate the data into a list and write it in one for with csv.writer.writerows().
Also you should pass the URL list to get_page_data() rather than accessing it from a global variable.
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)