I've written a script in python using multiprocessing module to scrape certain fields from a webpage. As I'm very new to write any script using multiprocessing, I've barely any Idea as to whether I did everything in the right way. It works errorlessly though.

Here goes the full script:

import requests 
from lxml.html import fromstring
from multiprocessing import Pool

link = "https://www.yellowpages.com/search?search_terms=coffee&geo_location_terms=Los%20Angeles%2C%20CA&page={}"

def create_links(url):
    response = requests.get(url).text
    tree = fromstring(response)
    for title in tree.cssselect("div.info"):
        name = title.cssselect("a.business-name span")[0].text
        try:
            street = title.cssselect("span.street-address")[0].text
        except IndexError: street = ""
        try:
            phone = title.cssselect("div[class^=phones]")[0].text
        except IndexError: phone = ""
        print(name, street, phone)

if __name__ == '__main__':
    links = [link.format(page) for page in range(1,4)]
    with Pool(4) as p:
        p.map(create_links, links)

Any idea to make it more robust (if there are rooms) will be highly appreciated.

I've written a script in Python using the multiprocessing module to scrape values from web pages (one page per subprocess). As I'm very new to multiprocessing, I'm not sure whether I did everything in the right way. It works without error, though.

Here goes the full script:

import requests 
from lxml.html import fromstring
from multiprocessing import Pool

link = "https://www.yellowpages.com/search?search_terms=coffee&geo_location_terms=Los%20Angeles%2C%20CA&page={}"

def create_links(url):
    response = requests.get(url).text
    tree = fromstring(response)
    for title in tree.cssselect("div.info"):
        name = title.cssselect("a.business-name span")[0].text
        try:
            street = title.cssselect("span.street-address")[0].text
        except IndexError: street = ""
        try:
            phone = title.cssselect("div[class^=phones]")[0].text
        except IndexError: phone = ""
        print(name, street, phone)

if __name__ == '__main__':
    links = [link.format(page) for page in range(1,4)]
    with Pool(4) as p:
        p.map(create_links, links)

Any idea to make it more robust will be highly appreciated.

I've written a script in python using multiprocessing module to scrape certain fields from a webpage. As I'm very new to write any script using multiprocessing, I've barely any Idea as to whether I did everything in the right way. It works errorlessly though.

Here goes the full script:

import requests 
from lxml.html import fromstring
from multiprocessing import Pool

link = "https://www.yellowpages.com/search?search_terms=coffee&geo_location_terms=Los%20Angeles%2C%20CA&page={}"

def create_links(url):
    response = requests.get(url).text
    tree = fromstring(response)
    for title in tree.cssselect("div.info"):
        name = title.cssselect("a.business-name span")[0].text
        try:
            street = title.cssselect("span.street-address")[0].text
        except IndexError: street = ""
        try:
            phone = title.cssselect("div[class^=phones]")[0].text
        except IndexError:
            phone = ""
        print(name, street, phone)

if __name__ == '__main__':
    links = [link.format(page) for page in range(1,4)]
    with Pool(4) as p:
        p.map(create_links, links)

Any idea to make it more robust (if there are rooms) will be highly appreciated.

I've written a script in python using multiprocessing module to scrape certain fields from a webpage. As I'm very new to write any script using multiprocessing, I've barely any Idea as to whether I did everything in the right way. It works errorlessly though.

Here goes the full script:

import requests 
from lxml.html import fromstring
from multiprocessing import Pool

link = "https://www.yellowpages.com/search?search_terms=coffee&geo_location_terms=Los%20Angeles%2C%20CA&page={}"

def create_links(url):
    response = requests.get(url).text
    tree = fromstring(response)
    for title in tree.cssselect("div.info"):
        name = title.cssselect("a.business-name span")[0].text
        try:
            street = title.cssselect("span.street-address")[0].text
        except IndexError: street = ""
        try:
            phone = title.cssselect("div[class^=phones]")[0].text
        except IndexError: phone = ""
        print(name, street, phone)

if __name__ == '__main__':
    links = [link.format(page) for page in range(1,4)]
    with Pool(4) as p:
        p.map(create_links, links)

Any idea to make it more robust (if there are rooms) will be highly appreciated.