Skip to content

Instantly share code, notes, and snippets.

@scrapehero
scrapehero / amazon_product.py
Last active August 14, 2022 03:03
from lxml import html
import csv
import os
import requests
from exceptions import ValueError
from time import sleep
from random import randint
def parse(url):
headers = {
@scrapehero
scrapehero / amazon_review_scraper.py
Last active August 5, 2022 10:59
Python Code to Scrape Customer Reviews from Amazon.com. Read more on https://www.scrapehero.com/how-to-scrape-amazon-product-reviews-using-python/
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Written as part of https://www.scrapehero.com/how-to-scrape-amazon-product-reviews-using-python/
from lxml import html
import json
import requests
import json,re
from dateutil import parser as dateparser
from time import sleep
@scrapehero
scrapehero / nasdaq_finance.py
Last active July 3, 2022 06:38
Script to scrape financial data from NASDAQ
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import html
import requests
from time import sleep
import json
import argparse
from random import randint
@scrapehero
scrapehero / yelp_search.py
Last active April 7, 2022 18:31
Python 3 code to extract business listings from Yelp.com
from lxml import html
import unicodecsv as csv
import requests
from time import sleep
import re
import argparse
import json
def parse(url):
@scrapehero
scrapehero / amazon-reviews.json
Last active February 25, 2022 23:52
Sitemap to extract data of review listings of a single product on Amazon.com using Web Scraper Chrome Extension. Instructions - https://www.scrapehero.com/amazon-review-scraper/
{
"_id": "amazon_reviews",
"startUrl": [
"https://www.amazon.com/Screen-Protector-SPARIN-Tempered-Glass/product-reviews/B013JZCAZK/ref=cm_cr_dp_d_show_all_btm?ie=UTF8&reviewerType=all_reviews"
],
"selectors": [
{
"id": "review",
"type": "SelectorElement",
"parentSelectors": [
@scrapehero
scrapehero / amazon_bestseller.json
Created November 2, 2018 12:53
JSON Sitemap to scrape amazon bestseller listings from Amazon using Web Scraper Chrome Extension
{
"_id":"amazon_pet",
"startUrl":[
"https://www.amazon.com/Best-Sellers-Pet-Supplies/zgbs/pet-supplies/ref=zg_bs_nav_0"
],
"selectors":[
{
"id":"product",
"type":"SelectorElement",
"parentSelectors":[
@scrapehero
scrapehero / zillow.py
Created May 9, 2017 15:00
Python script to find real estate listings of properties up for sale on zillow.com
from lxml import html
import requests
import unicodecsv as csv
from exceptions import ValueError
import argparse
def parse(zipcode,filter=None):
if filter=="newest":
url = "https://www.zillow.com/homes/for_sale/{0}/0_singlestory/days_sort".format(zipcode)
@scrapehero
scrapehero / yelp.py
Last active December 18, 2021 13:28
Python 2 code to extract business listings from Yelp.com
from lxml import html
import unicodecsv as csv
import requests
from time import sleep
import re
import argparse
import json
def parse(url):
@scrapehero
scrapehero / linkedin_scraper.py
Last active December 6, 2021 18:13
Python script to scrape a company details from a public company page on LinkedIn.com. Written as part of How to Scrape educational post - https://www.scrapehero.com/tutorial-scraping-linkedin-for-public-company-data/
from lxml import html
import csv, os, json
import requests
from exceptions import ValueError
from time import sleep
def linkedin_companies_parser(url):
for i in range(5):
try:
@scrapehero
scrapehero / glassdoor.py
Last active December 2, 2021 12:29
Python 3 code to extract job listings from Glassdoor.com
from lxml import html, etree
import requests
import re
import os
import sys
import unicodecsv as csv
import argparse
import json
def parse(keyword, place):