I was trying to scrap link which has ajax call for pagination.
I am trying to crawl http://www.demo.com link. and in .py file I provided this code for restrict XPATH and coding is:
# -*- coding: utf-8 -*-
import scrapy
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.contrib.spiders import sumSpider, Rule
from scrapy.selector import HtmlXPathSelector
from sum.items import sumItem
class Sumspider1(sumSpider):
name = 'sumDetailsUrls'
allowed_domains = ['sum.com']
start_urls = ['http://www.demo.com']
rules = (
Rule(LinkExtractor(restrict_xpaths='.//ul[#id="pager"]/li[8]/a'), callback='parse_start_url', follow=True),
)
#use parse_start_url if your spider wants to crawl from first page , so overriding
def parse_start_url(self, response):
print '********************************************1**********************************************'
#//div[#class="showMoreCars hide"]/a
#.//ul[#id="pager"]/li[8]/a/#href
self.log('Inside - parse_item %s' % response.url)
hxs = HtmlXPathSelector(response)
item = sumItem()
item['page'] = response.url
title = hxs.xpath('.//h1[#class="page-heading"]/text()').extract()
print '********************************************title**********************************************',title
urls = hxs.xpath('.//a[#id="linkToDetails"]/#href').extract()
print '**********************************************2***url*****************************************',urls
finalurls = []
for url in urls:
print '---------url-------',url
finalurls.append(url)
item['urls'] = finalurls
return item
My items.py file contains
from scrapy.item import Item, Field
class sumItem(Item):
# define the fields for your item here like:
# name = scrapy.Field()
page = Field()
urls = Field()
Still I'm not getting exact output not able to fetch all pages when I am crawling it.
I hope the below code will help.
somespider.py
# -*- coding: utf-8 -*-
import scrapy
import re
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import Selector
from scrapy.spider import BaseSpider
from demo.items import DemoItem
from selenium import webdriver
def removeUnicodes(strData):
if(strData):
strData = strData.encode('utf-8').strip()
strData = re.sub(r'[\n\r\t]',r' ',strData.strip())
return strData
class demoSpider(scrapy.Spider):
name = "domainurls"
allowed_domains = ["domain.com"]
start_urls = ['http://www.domain.com/used/cars-in-trichy/']
def __init__(self):
self.driver = webdriver.Remote("http://127.0.0.1:4444/wd/hub", webdriver.DesiredCapabilities.HTMLUNITWITHJS)
def parse(self, response):
self.driver.get(response.url)
self.driver.implicitly_wait(5)
hxs = Selector(response)
item = DemoItem()
finalurls = []
while True:
next = self.driver.find_element_by_xpath('//div[#class="showMoreCars hide"]/a')
try:
next.click()
# get the data and write it to scrapy items
item['pageurl'] = response.url
item['title'] = removeUnicodes(hxs.xpath('.//h1[#class="page-heading"]/text()').extract()[0])
urls = self.driver.find_elements_by_xpath('.//a[#id="linkToDetails"]')
for url in urls:
url = url.get_attribute("href")
finalurls.append(removeUnicodes(url))
item['urls'] = finalurls
except:
break
self.driver.close()
return item
items.py
from scrapy.item import Item, Field
class DemoItem(Item):
page = Field()
urls = Field()
pageurl = Field()
title = Field()
Note:
You need to have selenium rc server running because HTMLUNITWITHJS works with selenium rc only using Python.
Run your selenium rc server issuing the command :
java -jar selenium-server-standalone-2.44.0.jar
Run your spider using command:
spider crawl domainurls -o someoutput.json
You can check with your browser how the requests are made.
Behind the scene, right after you click on that button "show more cars" your browser will request a JSON data to feed your next page. You can take advantage of this fact and deal directly with the JSON data without the necessity to work with a JavaScript engine as Selenium or PhantomJS.
In your case, as the first step you should simulate an user scrolling down the page given by your start_url parameter and profile at the same time your network requests to discover the endpoint used by the browser to request that JSON. To discover this endpoint in general there is a XHR(XMLHttpRequest) section on the browser's profile tool as here in Safari where you can navigate thought all resources/endpoints used to request the data.
Once you discover this endpoint it's a straightforward task: you give your Spider as start_url the endpoint that you just discovered and according you process and navigate through the JSON's you can discover if it a next page to request.
P.S.: I saw for you that the endpoint url is http://www.carwale.com/webapi/classified/stockfilters/?city=194&kms=0-&year=0-&budget=0-&pn=2
In this case my browser requested the second page, as you can see in the parameter pn. It's is important you set the some header parameters before you send the request. I noticed in your case the headers are:
Accept text/plain, /; q=0.01
Referer http://www.carwale.com/used/cars-in-trichy/
X-Requested-With XMLHttpRequest
sourceid 1
User-Agent Mozilla/5.0...
Related
I'm not sure if this is the correct place for this question.
Here's my question:
If I run scrapy, it can't see the email addresses in the page source. The page has email addresses that are visible only when you hover over a user with an email address .
When I run my spider, I get no emails. What am I doing wrong?
Thank You.
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
import re
class MailsSpider(CrawlSpider):
name = 'mails'
allowed_domains = ['biorxiv.org']
start_urls = ['https://www.biorxiv.org/content/10.1101/2022.02.28.482253v3']
rules = (
Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
)
def parse_item(self, response):
emals = re.findall(r'[\w\.]+#[\w\.]+',response.text)
print(response.url)
print(emails)
Assuming you're allowed to scrape email contacts from a public website,
as said, scrapy does not loads js scripts, you need a full render browser like Playwright to get the address.
I've wrote down a quick and dirty example on how it could work, you can start from here if you wish (after you've installed playwright of course)
import scrapy
from scrapy.http import Request, FormRequest
from playwright.sync_api import sync_playwright
from scrapy.http import HtmlResponse
class PhaseASpider(scrapy.Spider):
name = "test"
def start_requests(self):
yield Request('https://www.biorxiv.org/content/10.1101/2022.02.28.482253v3', callback=self.parse_page)
def parse_page(self,response):
with sync_playwright() as p:
browser = p.firefox.launch(headless=False)
self.page = browser.new_page().
url='https://www.biorxiv.org/content/10.1101/2022.02.28.482253v3'
self.page.goto(url)
self.page.wait_for_load_state("load")
html_page=self.page.content()
response_sel = HtmlResponse(url="my HTML string", body=html_page, encoding='utf-8')
mails=response_sel.xpath('//a[contains(#href, "mailto")]/#href').extract()
for mail in mails:
print(mail.split('mailto:')[1])
This is my first question here and I'm learning how to code by myself so please bear with me.
I'm working on a final CS50 project which I'm trying to built a website that aggregates online Spanish course from edx.org and other open online couses websites maybe. I'm using scrapy framework to scrap the filter results of Spanish courses on edx.org... Here is my first scrapy spider which I'm trying to get in each courses link to then get it's name (after I get the code right, also get the description, course url and more stuff).
from scrapy.item import Field, Item
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractor import LinkExtractor
from scrapy.loader import ItemLoader
class Course_item(Item):
name = Field()
#description = Field()
#img_url = Field()
class Course_spider(CrawlSpider):
name = 'CourseSpider'
allowed_domains = ['https://www.edx.org/']
start_urls = ['https://www.edx.org/course/?language=Spanish']
rules = (Rule(LinkExtractor(allow=r'/course'), callback='parse_item', follow='True'),)
def parse_item(self, response):
item = ItemLoader(Course_item, response)
item.add_xpath('name', '//*[#id="course-intro-heading"]/text()')
yield item.load_item()
When I run the spider with "scrapy runspider edxSpider.py -o edx.csv -t csv" I get an empty csv file and I also think is not getting into the right spanish courses results.
Basically I want to get in each courses of this link edx Spanish courses and get the name, description, provider, page url and img url.
Any ideas for why might be the problem?
You can't get edx content with a simple request, it uses javascript rendering for getting the course element dynamically, so CrawlSpider won't work on this case, because you need to find specific elements inside the response body to generate a new Request that will get what you need.
The real request (to get the urls of the courses) is this one, but you need to generate it from the previous response body (although you could just visit it an also get the correct data).
So, to generate the real request, you need data that is inside a script tag:
from scrapy import Spider
import re
import json
class Course_spider(Spider):
name = 'CourseSpider'
allowed_domains = ['edx.org']
start_urls = ['https://www.edx.org/course/?language=Spanish']
def parse(self, response):
script_text = response.xpath('//script[contains(text(), "Drupal.settings")]').extract_first()
parseable_json_data = re.search(r'Drupal.settings, ({.+})', script_text).group(1)
json_data = json.loads(parseable_json_data)
...
Now you have what you need on json_data and only need to create the string URL.
This page use JavaScript to get data from server and add to page.
It uses urls like
https://www.edx.org/api/catalog/v2/courses/course-v1:IDBx+IDB33x+3T2017
Last part is course's number which you can find in HTML
<main id="course-info-page" data-course-id="course-v1:IDBx+IDB33x+3T2017">
Code
from scrapy.http import Request
from scrapy.item import Field, Item
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractor import LinkExtractor
from scrapy.loader import ItemLoader
import json
class Course_spider(CrawlSpider):
name = 'CourseSpider'
allowed_domains = ['www.edx.org']
start_urls = ['https://www.edx.org/course/?language=Spanish']
rules = (Rule(LinkExtractor(allow=r'/course'), callback='parse_item', follow='True'),)
def parse_item(self, response):
print('parse_item url:', response.url)
course_id = response.xpath('//*[#id="course-info-page"]/#data-course-id').extract_first()
if course_id:
url = 'https://www.edx.org/api/catalog/v2/courses/' + course_id
yield Request(url, callback=self.parse_json)
def parse_json(self, response):
print('parse_json url:', response.url)
item = json.loads(response.body)
return item
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
'FEED_FORMAT': 'csv', # csv, json, xml
'FEED_URI': 'output.csv', #
})
c.crawl(Course_spider)
c.start()
from scrapy.http import Request
from scrapy import Spider
import json
class edx_scraper(Spider):
name = "edxScraper"
start_urls = [
'https://www.edx.org/api/v1/catalog/search?selected_facets[]=content_type_exact%3Acourserun&selected_facets[]=language_exact%3ASpanish&page=1&page_size=9&partner=edx&hidden=0&content_type[]=courserun&content_type[]=program&featured_course_ids=course-v1%3AHarvardX+CS50B+Business%2Ccourse-v1%3AMicrosoft+DAT206x+1T2018%2Ccourse-v1%3ALinuxFoundationX+LFS171x+3T2017%2Ccourse-v1%3AHarvardX+HDS2825x+1T2018%2Ccourse-v1%3AMITx+6.00.1x+2T2017_2%2Ccourse-v1%3AWageningenX+NUTR101x+1T2018&featured_programs_uuids=452d5bbb-00a4-4cc9-99d7-d7dd43c2bece%2Cbef7201a-6f97-40ad-ad17-d5ea8be1eec8%2C9b729425-b524-4344-baaa-107abdee62c6%2Cfb8c5b14-f8d2-4ae1-a3ec-c7d4d6363e26%2Ca9cbdeb6-5fc0-44ef-97f7-9ed605a149db%2Cf977e7e8-6376-400f-aec6-84dcdb7e9c73'
]
def parse(self, response):
data = json.loads(response.text)
for course in data['objects']['results']:
url = 'https://www.edx.org/api/catalog/v2/courses/' + course['key']
yield response.follow(url, self.course_parse)
if 'next' in data['objects'] is not None:
yield response.follow(data['objects']['next'], self.parse)
def course_parse(self, response):
course = json.loads(response.text)
yield{
'name': course['title'],
'effort': course['effort'],
}
I making a web crawler with Scrapy which will visit a list of URLs and return all cookies from these domains including those set by third parties.
This spider follows all links on the given URLs and writes each cookie in a separate text file:
from scrapy.linkextractors import LinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.item import Item, Field
import requests
class MyItem(Item):
url= Field()
class MySpider(CrawlSpider):
name = "a"
start_urls = ['http://www.dailymail.co.uk/home/index.html']
rules = (Rule(LinkExtractor(), callback='parse_url', follow=False), )
def parse_url(self, response):
item = MyItem()
item['url'] = response.url
filename = '%s.txt'
if response.headers.getlist('Set-Cookie'):
page = response.url.split("/")[-2]
with open(filename, 'wb') as f:
for cookie in response.headers.getlist('Set-Cookie'):
f.write(cookie)
This results in 11 different text files each containing a cookie. The result is inconsistent with that produced by the website cookie-checker.com.
Is there a way to find all cookies set on a page using Scrapy?
Some cookies could be set via client-side(Javascript)
I suggest you use Selenium + PhantomJS to collect all client/server side cookies.
from selenium import webdriver
driver = webdriver.PhantomJS()
driver.get('http://www.example.com/')
cookies = driver.get_cookies()
I have made a spider using scrapy and I am trying to save download links into a (python) list, so I can later call a list entry using downloadlist[1].
But scrapy saves the urls as items instead of as a list. Is there a way to append each url into a list?
from scrapy.selector import HtmlXPathSelector
from scrapy.spider import BaseSpider
from scrapy.http import Request
import scrapy
from scrapy.linkextractors import LinkExtractor
DOMAIN = 'some-domain.com'
URL = 'http://' +str(DOMAIN)
linklist = []
class subtitles(scrapy.Spider):
name = DOMAIN
allowed_domains = [DOMAIN]
start_urls = [
URL
]
# First parse returns all the links of the website and feeds them to parse2
def parse(self, response):
hxs = HtmlXPathSelector(response)
for url in hxs.select('//a/#href').extract():
if not ( url.startswith('http://') or url.startswith('https://') ):
url= URL + url
yield Request(url, callback=self.parse2)
# Second parse selects only the links that contains download
def parse2(self, response):
le = LinkExtractor(allow=("download"))
for link in le.extract_links(response):
yield Request(url=link.url, callback=self.parse2)
print link.url
# prints list of urls, 'downloadlist' should be a list but isn't.
downloadlist = subtitles()
print downloadlist
You are misunderstanding how classes work, you are calling a class here not a function.
Think about it this way, your spider tht you define in class MySpider(Spider) is a template that is used by scrapy engine; when you start scrapy crawl myspider scrapy starts up an engine and reads your template to create an object that will be used to process various responses.
So your idea here can be simply translated to:
def parse2(self, response):
le = LinkExtractor(allow=("download"))
for link in le.extract_links(response):
yield {'url': link.urk}
If you call this with scrapy crawl myspider -o items.json you'll get all of the download links in json format.
There no reason to save downloads of to a list since it will be no longer of this spider template (class) that you wrote up and essentially it will have no purpose.
I'm currently using a combination of Scrapy and Selenium to quickly search the USPTO TradeMark database. These pages have a session token attached.
The things I've tried and read about don't seem to be integrated enough- meaning that while Selenium can pass found URLs to scrapy, scrapy makes a new request to that page, thus invalidating the token, so I need Selenium to deliver the HTML to scrapy for parsing. Is this possible?
# -*- coding: utf-8 -*-
# from terminal run: scrapy crawl trademarks -o items.csv -t csv
import time
import scrapy
from scrapy.http import Request
from scrapy.item import Item, Field
from scrapy.selector import Selector
from scrapy.spiders import CrawlSpider
from selenium import webdriver
class TrademarkscrapeItem(scrapy.Item):
category = Field()
wordmark = Field()
registrant = Field()
registration_date = Field()
description = Field()
class TradeMarkSpider(CrawlSpider):
name = "trademarks"
allowed_domains = ["uspto.gov"]
start_urls = ['http://www.uspto.gov']
def __init__(self):
self.driver = webdriver.Firefox()
def parse(self, response):
# Navigate through the site to get to the page I want to scrape
self.driver.get(response.url)
next = self.driver.find_element_by_xpath("//*[#id='menu-84852-1']/a")
next.click()
time.sleep(2) # Let any js render in page
next = self.driver.find_element_by_xpath("//*[#id='content']/article/ul[1]/li[1]/article/h4/a")
next.click()
time.sleep(2)
# How to get this next part to point at Selenium-delivered HTML?
TradeDict = {}
SelectXpath = Selector(SeleniumHTML).xpath #SeleniumHTML is psuedoCode
TradeDict['description'] = SelectXpath("//*[#id='content']/article/div/p/text()").extract()
self.driver.close()
return TradeDict