We Keep Coding

extract names in custom <h2> but It is extracted many times beautifulsoup

I am trying to extract names in custom <h2>, but the names I want are extracted many times.
how to fix this problem and extract it one time
The page I am pulling data from
here
import requests
import csv
from bs4 import BeautifulSoup
from itertools import zip_longest
lawy_name = []
page_num = 1
phone = []
logo = []
website = []
links = []
while True:
try:
result = requests.get(f"https://example.com/motor-vehicle-accidents/texas/houston/page{page_num}/")
src = result.content
soup = BeautifulSoup(src, "lxml")
page_limit = int("126")
if(page_num > page_limit // 25):
print("page ended, terminate")
break
lawy_names = soup.select('div.poap.serp-container.lawyer h2.indigo_text')
for i in range(len(lawy_names)) :
lawy_name.append(lawy_names[i].text.strip())
links.append(lawy_names[i].find("a").attrs["href"])
for link in links:
result = requests.get(link)
src = result.content
soup = BeautifulSoup(src, "lxml")
phones = soup.find("a", {"class":"profile-phone-header profile-contact-btn"})
phone.append(phones["href"])
logos = soup.find("div", {"class":"photo-container"})
logo.append(logos.find('img')['src'])
websites = soup.find("a", {"class":"profile-website-header","id":"firm_website"})
website.append(websites.text.strip())
page_num +=1
print("page switched")
except:
print("error")
break
file_list = [lawy_name, phone, website, logo]
exported = zip_longest(*file_list)
with open("/Users/dsoky/Desktop/fonts/Moaaz.csv", "w") as myfile:
wr = csv.writer(myfile)
wr.writerow(["lawyer name","phone","website","logo"])
wr.writerows(exported)
Problem:

The website does produce a lot of duplicate entries. You could probably assume that all entries have unique names, as such a dictionary could be used to hold all of your data. Simply skip any entries for which you have already seen the same name. For example:
from bs4 import BeautifulSoup
import requests
import csv
lawyers = {}
page_num = 1
while True:
print(f"Page {page_num}")
req = requests.get(f"https://example.com/motor-vehicle-accidents/texas/houston/page{page_num}/")
soup = BeautifulSoup(req.content, "lxml")
found = False
for id in ['sponsored_serps', 'ts_results', 'poap_results', 'basic_results']:
div_results = soup.find('div', id=id)
if div_results:
for result in div_results.find_all('div', class_='lawyer'):
name = result.h2.get_text(strip=True)
if name not in lawyers:
print(' ', name)
link = result.h2.a['href']
req_details = requests.get(link)
soup_details = BeautifulSoup(req_details.content, "lxml")
a_phone = soup_details.find("a", {"class":"profile-phone-header profile-contact-btn"}, href=True)
if a_phone:
phone = a_phone['href']
else:
phone = None
div_logo = soup_details.find("div", {"class":"photo-container"})
if div_logo.img:
logo = div_logo.img['src']
else:
logo = None
a_website = soup_details.find("a", {"class":"profile-website-header","id":"firm_website"})
if a_website:
website = a_website.get_text(strip=True)
else:
website = None
lawyers[name] = [phone, logo, website]
found = True
# Keep going until no new names found
if found:
page_num += 1
else:
break
with open('Moaaz.csv', 'w', newline='') as f_output:
csv_output = csv.writer(f_output)
csv_output.writerow(['Name', 'Phone', 'Logo', 'Website'])
for name, details in lawyers.items():
csv_output.writerow([name, *details])

Beautiful soup doesn't scrape the data from the "next" pages

I am trying to scrape airbnb data using BeautifulSoup and Pandas. I checked a lot of tutorials and found the one I followed. The step in which the soup should scrape the data from the next page is not working, out of 15 pages, it scrapes only the first 2 or 3 pages or sometimes even none (even if the URLs of the pages are correct).
I cannot seem to understand why this happens and how to solve it. Can someone help out?
import requests
import bs4
import pandas as pd
import numpy as np
import csv
import time
url = 'https://www.airbnb.it/s/Italy/homes?checkin=2021-08-01&checkout=2021-08-02'
def get_page(url):
response = requests.get(url)
soup = bs4.BeautifulSoup(response.text, "html.parser")
return soup
def get_listings(soup):
result = []
result.extend(soup.find_all("div", {"class": "_8ssblpx"}))
return result
def get_listing_title(listing):
for l in listing:
try:
return str(l.find('div', {'class': '_1tanv1h'}).text)
except:
return None
def get_listing_subtitle(listing):
for l in listing:
try:
return str(l.find('span', {'class': '_1whrsux9'}).text)
except:
return None
def get_listing_info(listing):
for l in listing:
try:
return str(l.find_all('div', {'class': '_3c0zz1'})[0].text.lower())
except:
return None
def find_next_page(page):
base_url = "https://www.airbnb.it"
try:
nextpage = base_url + get_page(url).find_all("div", attrs={"class": "_jro6t0"})[0].find("a", attrs={'class':'_za9j7e'})['href']
except:
nextpage = None
return nextpage
title = []
subtitle = []
info = []
while url is not None:
soup = get_page(url)
listings = get_listings(soup)
for l in listings:
title.append(get_listing_title(l))
subtitle.append(get_listing_subtitle(l))
info.append(get_listing_info(l))
time.sleep(5)
url = find_next_page(soup)
print(url)
airbnb_data = pd.DataFrame(data = {'title': title,
'subtitle': subtitle,
'info': info})
airbnb_data

Get data from product page and back Scraper

class Crawler():
def __init__(self):
self.pag = 1
i = 0
def get_urls(self,main_url):
self.url = 'https://www.test.ro/search/'+ main_url +'/p1'
self.filename = main_url
r = requests.get(self.url)
soup = BeautifulSoup(r.text, 'html.parser')
number_pages = soup.find(class_= 'row' )
last_page = number_pages.find_all('a')[len(number_pages.find_all('a'))-2].get("data-page")
for i in range(1, int(last_page)+1):
url.append('https://www.test.ro/search/'+ main_url +'/p' + str(i))
def print_urls(self):
for urls in url:
print (urls)
def scrape(self,url):
r = requests.get(url)
soup = BeautifulSoup(r.text, 'html.parser')
product_list = soup.find(class_ = 'page-container')
product_list_name = product_list.find_all('h2')
product_list_oldprice = product_list.find_all(class_ = 'product-old-price')
product_list_newprice = product_list.find_all(class_ = 'product-new-price')
for i in range(0, len(product_list_name)):
name = product_list_name[i].get_text().strip()
link = product_list_name[i].find('a').get('href')
#print(name)
#print(len(name))
try:
price = product_list_oldprice[i].contents[0].get_text()
price = price[:-6]
#print(price)
except IndexError:
#print("no old price")
#print(product_list_newprice[i].contents[0])
with open(self.filename+'.csv', 'a', encoding = 'utf-8', newline='') as csv_file:
file_is_empty = os.stat(self.filename+'.csv').st_size == 0
fieldname = ['name','link', 'price_old', 'price_actualy']
writer = csv.DictWriter(csv_file, fieldnames = fieldname)
if file_is_empty:
writer.writeheader()
writer.writerow({'name':name,'link':link, 'price_old':price, 'price_actualy':product_list_newprice[i].contents[0]})
if __name__=='__main__':
print("Search for product: ")
urlsearch = input()
starttime = time.time()
scraper = Crawler()
scraper.get_urls(urlsearch)
scraper.print_urls()
#scraper.scrape(url[0])
pool = multiprocessing.Pool()
pool.map(scraper.scrape,url)
pool.close()
print('That took {} seconds'.format(time.time() - starttime))
So I have this scraper, it works perfectly on any website bag but only on the product page.
I did it for a specific website, but how could I go on each page to take the data from the product and give it back and do it all over again?
Is such a thing possible?
I now take the data from the products page, ie name, link, price.
You have divs there too.
Can I help href?

In this case you need to create a category scraper that safes all product urls first. Scrape all urls and go through all the category's and for example safe them to csv first (the product urls). Then you can take all the product urls from the CSV and loop through all of them.

Script crawls only the first page instead of multiple pages

I am trying to crawl multiple pages of a website. But the program can only crawl the first page.
import requests
from bs4 import BeautifulSoup
import re
import json
import time
def make_soup(url):
source = requests.get(url).text
soup = BeautifulSoup(source, 'lxml')
pattern = re.compile(r'window.__WEB_CONTEXT__={pageManifest:(\{.*\})};')
script = soup.find("script", text=pattern)
jsonData = pattern.search(script.text).group(1)
pattern_number = re.compile(r'\"[0-9]{9,12}\":(\{\"data\":\{\"cachedFilters\":(.*?)\}\}),\"[0-9]{9,11}\"')
jsonData2 = pattern_number.search(jsonData).group(1)
dictData = json.loads(jsonData2)
return dictData
def get_reviews(dictData):
""" Return a list of five dicts with reviews.
"""
all_dictionaries = []
for data in dictData['data']['locations']:
for reviews in data['reviewListPage']['reviews']:
review_dict = {}
review_dict["reviewid"] = reviews['id']
review_dict["reviewurl"] = reviews['absoluteUrl']
review_dict["reviewlang"] = reviews['language']
review_dict["reviewdate"] = reviews['createdDate']
userProfile = reviews['userProfile']
review_dict["author"] = userProfile['displayName']
all_dictionaries.append(review_dict)
return all_dictionaries
def main():
url = 'https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-Coronado_Hotel-Zurich.html#REVIEWS'
dictData = make_soup(url)
review_list = get_reviews(dictData) # list with five dicts
#print(review_list)
page_number = 5
while page_number <= 260: # number in the URL
next_url = 'https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-or' + str(page_number) + '-Coronado_Hotel-Zurich.html#REVIEWS'
dictData = make_soup(url)
review_list2 = get_reviews(dictData)
print(review_list2)
page_number += 5
time.sleep(0.5)
if __name__ == "__main__":
main()
And I'm not sure if I can crawl multiple pages with this URL. On the website there are 54 pages, but in the URL I always have to add the number 5, like this:
Page 1
https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-Coronado_Hotel-Zurich.html#REVIEWS
Page2
https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-or5-Coronado_Hotel-Zurich.html#REVIEWS
Page3
https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-or10-Coronado_Hotel-Zurich.html#REVIEWS
I don't know if this is a good idea.
Do you have any suggestions? Thank you in advance!

You assing new url to next_url but you use url to read page.
next_url = 'https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-or' + str(page_number) + '-Coronado_Hotel-Zurich.html#REVIEWS'
dictData = make_soup(url)
You have to rename variable
url = 'https://www.tripadvisor.ch/Hotel_Review-g188113-d228146-Reviews-or' + str(page_number) + '-Coronado_Hotel-Zurich.html#REVIEWS'
dictData = make_soup(url)

How to make request to new url?

I already have this code, helped by a friend before. I already get all the links in the site. I want to get the name, merk, price, picture, description of the product, and the link of the product. The description's product only appear if we click the product.
I'm a beginner in Python.
from bs4 import BeautifulSoup
import urllib.request
count = 1
url = "https://www.sociolla.com/155-foundation?p=%d"
def get_url(url):
req = urllib.request.Request(url)
return urllib.request.urlopen(req)
expected_url = url % count
response = get_url(expected_url)
link = []
name = []
merk = []
price = []
pic = []
description = []
while (response.url == expected_url):
#print("GET {0}".format(expected_url))
soup = BeautifulSoup(response.read(), "html.parser")
products = soup.find("div",{"id":"product-list-grid"})
for i in products:
data = products.findAll("div",{"class":"product-item"})
for j in range(0, len(data)):
link.append(data[j]["data-eec-href"])
count += 1
expected_url = url % count
response = get_url(expected_url)
print(len(link))
"""
import csv
dataset=zip(link, merk, name, pic, price, description)
with open("foundation_sociolla.csv","w", newline='') as csvfile:
writer=csv.writer(csvfile)
header=['link', 'merk', 'name', 'pic', 'price', 'description']
writer.writerow(header)
writer.writerows(dataset)
"""

You need to make a request to the URL. Parse the content of that request and extract the data you want.
from bs4 import BeautifulSoup
import urllib.request
count = 1
url = "https://www.sociolla.com/155-foundation?p=%d"
def get_url(url):
req = urllib.request.Request(url)
return urllib.request.urlopen(req)
expected_url = url % count
response = get_url(expected_url)
link = []
name = []
make = []
price = []
pic = []
description = []
while response.url == expected_url:
soup = BeautifulSoup(response.read(), "html.parser")
for product in soup.select("div.product-item"):
product_url = (product['data-eec-href'])
link.append(product_url)
product_response = get_url(product_url)
product_soup = BeautifulSoup(product_response.read(), "html.parser")
product_pic = product_soup.select('img#bigpic')[0]['src']
pic.append(product_pic)
product_price = product_soup.select('span#our_price_display')[0].text.strip()
price.append(product_price)
product_name = product_soup.select('div.detail-product-logo p')[0].text.strip()
name.append(product_name)
product_make = product_soup.select('div.detail-product-logo h3')[0].text.strip()
make.append(product_make)
product_description = product_soup.select('div#Details article')[0].text.strip()
description.append(product_description)
print(product_url, product_pic, product_price, product_name, product_make, product_description)
count += 1
expected_url = url % count
response = get_url(expected_url)
But if your going to scrape a lot of pages you are much better off using something like Scrapy https://scrapy.org/