This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 = { |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from lxml import html | |
import unicodecsv as csv | |
import requests | |
from time import sleep | |
import re | |
import argparse | |
import json | |
def parse(url): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"_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": [ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"_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":[ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from lxml import html | |
import unicodecsv as csv | |
import requests | |
from time import sleep | |
import re | |
import argparse | |
import json | |
def parse(url): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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): |