This file contains hidden or 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
# -*- coding: utf-8 -*- | |
import scrapy | |
class ChannelSpider(scrapy.Spider): | |
name = 'channel' | |
allowed_domains = ['channelcrawler.com'] | |
def start_requests(self): | |
yield scrapy.Request( |
This file contains hidden or 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
# -*- coding: utf-8 -*- | |
import scrapy | |
import json | |
class FreelancerComRuSpider(scrapy.Spider): | |
name = 'freelancer_com_ru' | |
allowed_domains = ['www.freelancer.com.ru'] | |
iDisplayStart = 0 |
This file contains hidden or 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
# -*- coding: utf-8 -*- | |
import scrapy | |
import hashlib | |
from scrapy.http import FormRequest | |
class ItrlogSpider(scrapy.Spider): | |
name = 'itrlog' | |
start_urls = ['http://itr.lacecal.es/page/index.php?s=login'] | |
This file contains hidden or 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
# -*- coding: utf-8 -*- | |
from time import sleep | |
import scrapy | |
from scrapy.selector import Selector | |
from selenium.common.exceptions import ElementClickInterceptedException | |
from selenium import webdriver | |
from selenium.webdriver.chrome.options import Options | |
from shutil import which | |
This file contains hidden or 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
# -*- coding: utf-8 -*- | |
import scrapy | |
from scrapy.http import FormRequest | |
class QuotesSpider(scrapy.Spider): | |
name = 'quotes' | |
allowed_domains = ['quotes.toscrape.com'] | |
start_urls = [ | |
'http://quotes.toscrape.com/login' | |
] |
This file contains hidden or 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
# -*- coding: utf-8 -*- | |
import scrapy | |
from scrapy.selector import Selector | |
from scrapy_splash import SplashRequest | |
import logging | |
import json | |
from w3lib.http import basic_auth_header | |
class ListingsSpider(scrapy.Spider): | |
name = 'listings' |
This file contains hidden or 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
function main(splash, args) | |
headers ={ | |
['User-Agent'] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36", | |
['cookie'] = 'AKAM_CLIENTID=900310a15c7997a11d2fb87ba96b454b; gb_lang=en; gb_pipeline=GB; _ga=GA1.2.1217688139.1555317699; gb_countryCode=DZ; _fbp=fb.1.1555317699787.334894344; gb_currencyCode=USD; od=gzguxgyfmdgy1555317700622; gb_vid=8153f54a-97b5-a192-9676-c0fd4028b6ae; gb_guid=407704339; _gcl_au=1.1.124645050.1563146349; __atssc=google%3B1; __atuvc=8%7C30%2C12%7C31; aff_mss_info_bak={"bak":"bak"}; linkid=19147949; aff_mss_info={"lkid":"19147949"}; landingUrl=https://www.gearbest.com/flash-sale.html; _ngroup=[{"tid":3,"v":[{"n":"_nlnkid","v":"19147949"}],"lt":1569691945,"ct":1569691945}]; _gid=GA1.2.1136355824.1569691945; _dc_gtm_UA-48073707-1=1; ak_bmsc=D9330EDB75843DE802EF9D0F1461508B4F8C5EFE587D000032998F5D414ED406~plzK7NKpuYIFP7MISrzxYqivqeIm3UHRCKb5HR+sD9QjKiG5Z/HSktEavkyeZWM5lCTwj5ne9MGYvNQF/qbdiExmEH7oJUvGi0D4jy |
This file contains hidden or 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 requests | |
script =''' | |
headers ={ | |
['User-Agent'] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36", | |
['cookie'] = 'AKAM_CLIENTID=900310a15c7997a11d2fb87ba96b454b; gb_lang=en; gb_pipeline=GB; _ga=GA1.2.1217688139.1555317699; gb_countryCode=DZ; _fbp=fb.1.1555317699787.334894344; gb_currencyCode=USD; od=gzguxgyfmdgy1555317700622; gb_vid=8153f54a-97b5-a192-9676-c0fd4028b6ae; gb_guid=407704339; _gcl_au=1.1.124645050.1563146349; __atssc=google%3B1; __atuvc=8%7C30%2C12%7C31; aff_mss_info_bak={"bak":"bak"}; linkid=19147949; aff_mss_info={"lkid":"19147949"}; landingUrl=https://www.gearbest.com/flash-sale.html; _ngroup=[{"tid":3,"v":[{"n":"_nlnkid","v":"19147949"}],"lt":1569691945,"ct":1569691945}]; _gid=GA1.2.1136355824.1569691945; _dc_gtm_UA-48073707-1=1; ak_bmsc=D9330EDB75843DE802EF9D0F1461508B4F8C5EFE587D000032998F5D414ED406~plzK7NKpuYIFP7MISrzxYqivqeIm3UHRCKb5HR+sD9QjKiG5Z/HSktEavkyeZWM5lCTwj5ne9MGYvNQF/qbdiExmEH7oJUvG |
This file contains hidden or 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 scrapy | |
from scrapy_splash import SplashRequest | |
class MySpide(scrapy.Spider): | |
name = 'google' | |
script = ''' | |
function main(splash) | |
local host = "proxy.crawlera.com" | |
local port = 8010 |
This file contains hidden or 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
__pycache__/ | |
.vscode/ | |
build/ | |
dbs/ | |
eggs/ | |
project.egg-info/ | |
*.json | |
*.csv |