View hotels_scraper.py
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 | |
from re import findall,sub | |
from lxml import html | |
from time import sleep | |
from selenium import webdriver | |
from pprint import pprint | |
from xvfbwrapper import Xvfb | |
def parse(url): | |
searchKey = "Las Vegas" # Change this to your city |
View linkedin_jobs_scraper.py
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 bs4 import BeautifulSoup | |
from requests import get | |
from re import sub | |
from json import loads,dump | |
from re import findall,sub | |
from unicodecsv import QUOTE_ALL,DictWriter | |
totalJobs = [] | |
def getPage(url): | |
""" |
View amazon_review_scraper.py
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 |
View yelp_business_details.py
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 json | |
import requests | |
from exceptions import ValueError | |
from time import sleep | |
import re,urllib | |
import argparse | |
def parse(url): | |
# url = "https://www.yelp.com/biz/frances-san-francisco" |
View linkedin_scraper.py
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: |
View yahoo_finance.py
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 | |
from time import sleep | |
import json | |
import argparse | |
from collections import OrderedDict | |
from time import sleep | |
def parse(ticker): | |
url = "http://finance.yahoo.com/quote/%s?p=%s"%(ticker,ticker) |
View expedia.py
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
import json | |
import requests | |
from lxml import html | |
from collections import OrderedDict | |
import argparse | |
def parse(source,destination,date): | |
for i in range(5): | |
try: | |
url = "https://www.expedia.com/Flights-Search?trip=oneway&leg1=from:{0},to:{1},departure:{2}TANYT&passengers=adults:1,children:0,seniors:0,infantinlap:Y&options=cabinclass%3Aeconomy&mode=search&origref=www.expedia.com".format(source,destination,date) |
View ebay_scraper.py
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
import argparse | |
from pprint import pprint | |
from traceback import format_exc | |
import requests | |
import unicodecsv as csv | |
from lxml import html | |
def parse(brand): |
View geocoder.py
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 requests import get | |
from pprint import pprint | |
from json import dump | |
from csv import QUOTE_ALL, DictWriter | |
API_KEY = 'XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX' | |
def address_resolver(json): | |
final = {} | |
if json['results']: | |
data = json['results'][0] | |
for item in data['address_components']: |
View captcha_resolver.py
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
import pytesseract | |
import sys | |
import argparse | |
try: | |
import Image | |
except ImportError: | |
from PIL import Image | |
from subprocess import check_output | |
OlderNewer