I am trying to scrape lynda.com courses and storing their info in a csv file. This is my code
# -*- coding: utf-8 -*-
import scrapy
import itertools
class LyndadevSpider(scrapy.Spider):
name = 'lyndadev'
allowed_domains = ['lynda.com']
start_urls = ['https://www.lynda.com/Developer-training-tutorials']
def parse(self, response):
#print(response.url)
titles = response.xpath('//li[#role="presentation"]//h3/text()').extract()
descs = response.xpath('//li[#role="presentation"]//div[#class="meta-description hidden-xs dot-ellipsis dot-resize-update"]/text()').extract()
links = response.xpath('//li[#role="presentation"]/div/div/div[#class="col-xs-8 col-sm-9 card-meta-data"]/a/#href').extract()
for title, desc, link in itertools.izip(titles, descs, links):
#print link
categ = scrapy.Request(link, callback=self.parse2)
yield {'desc': link, 'category': categ}
def parse2(self, response):
#getting categories by storing the navigation info
item = response.xpath('//ol[#role="navigation"]').extract()
return item
What I am trying to do here is that I am grabbing the titles, description of the list of tutorials and then navigating to the url and grabbing the categories in parse2.
However, I get results like this:
category,desc
<GET https://www.lynda.com/SVN-Subversion-tutorials/SVN-Java-Developers/552873-2.html>,https://www.lynda.com/SVN-Subversion-tutorials/SVN-Java-Developers/552873-2.html
<GET https://www.lynda.com/Java-tutorials/WebSocket-Programming-Java-EE/574694-2.html>,https://www.lynda.com/Java-tutorials/WebSocket-Programming-Java-EE/574694-2.html
<GET https://www.lynda.com/GameMaker-tutorials/Building-Physics-Based-Platformer-GameMaker-Studio-Using-GML/598780-2.html>,https://www.lynda.com/GameMaker-tutorials/Building-Physics-Based-Platformer-GameMaker-Studio-Using-GML/598780-2.html
How do I access the information that I want?
You need to yield a scrapy.Request in the parse method that parses the responses of start_urls (instead of yielding a dict). Also, I would rather loop over course items and extract the information for each course item separately.
I'm not sure what you mean exactly by categories. I suppose those are the tags you can see on the course details page at the bottom under Skills covered in this course. But I might be wrong.
Try this code:
# -*- coding: utf-8 -*-
import scrapy
class LyndaSpider(scrapy.Spider):
name = "lynda"
allowed_domains = ["lynda.com"]
start_urls = ['https://www.lynda.com/Developer-training-tutorials']
def parse(self, response):
courses = response.css('ul#category-courses div.card-meta-data')
for course in courses:
item = {
'title': course.css('h3::text').extract_first(),
'desc': course.css('div.meta-description::text').extract_first(),
'link': course.css('a::attr(href)').extract_first(),
}
request = scrapy.Request(item['link'], callback=self.parse_course)
request.meta['item'] = item
yield request
def parse_course(self, response):
item = response.meta['item']
#item['categories'] = response.css('div.tags a em::text').extract()
item['category'] = response.css('ol.breadcrumb li:last-child a span::text').extract_first()
return item
Related
I am having problems going through multiple pages. Here is my class for scrapy code called quotes.
class quotes(scrapy.Spider):
name = 'quotes'
start_urls = ['http://books.toscrape.com/?']
def parse(self, response):
all_links = response.css('.nav-list ul li')
for links in all_links:
link = links.css('a::attr(href)').get()
yield response.follow(link, callback = self.books_detail)
def books_detail(self, response):
yas = {
'title':[],
'price':[],
'availability':[],
'category':[]
}
yas['category'].append(response.css('h1::text').extract())
all_divs = response.css('.col-lg-3')
for div in all_divs:
link = div.css('.product_pod a::attr(href)').get()
title = response.follow(link, callback = self.get_title)
yas['price'].append(div.css('.price_color::text').extract())
yas['availability'].append(div.css('.availability::text')[1].extract())
yield yas
def get_title(self,response):
print('testing')
title = response.css('h1::text').extract()
yield {"title":title}
So I use a response.follow to goto function books_details and in that function, I again call response.follow to call get_title. I get the 'title' from get_title and the rest of the details from the main page.
I can scrape the information just fine from the books_details function and I can get the link of the title page just fine as well from the code line.
link = div.css('.product_pod a::attr(href)').get()
But using the response.follow I can not go to the get_title function.
Any help would be appreciated. Thanks.
You should yield request, not run it directly, and use meta= to send data to next parser
yield response.follow(link, callback=self.get_title, meta={'item': yas})
and in next parser you can get it
yas = response.meta['item']
and then you can add new values and yield all data
yas["title"] = response.css('h1::text').extract()
yield yas
See other example in Scrapy yeild items from multiple requests
Doc: Request and Response, Request.meta special keys
Minimal working code which you can put in one file and run as normal script (python script.py) without creating project.
There are other changes.
You shouldn't put all books to one list but yield every book separatelly. Scrapy will keep all results and when you use option to save in csv then it will save all results.
For every book you should create new dictionary. If you use the same dictionary many time then it will ovewrite data and you may get many result with the same data.
import scrapy
class QuotesSpider(scrapy.Spider):
name = 'quotes'
start_urls = ['http://books.toscrape.com/']
def parse(self, response):
all_links = response.css('.nav-list ul li')
for links in all_links:
link = links.css('a::attr(href)').get()
yield response.follow(link, callback=self.books_detail)
def books_detail(self, response):
all_divs = response.css('.col-lg-3')
for div in all_divs:
# every book in separated dictionary and it has to be new dictionary - because it could overwrite old data
book = {
'category': response.css('h1::text').extract(),
'price': div.css('.price_color::text').extract()[0].strip(),
'availability': div.css('.availability::text')[1].extract().strip(),
}
link = div.css('.product_pod a::attr(href)').get()
yield response.follow(link, callback=self.get_title, meta={'item': book})
def get_title(self, response):
book = response.meta['item']
print('testing:', response.url)
book["title"] = response.css('h1::text').extract()[0].strip()
yield book
# --- run without project and save in `output.csv` ---
from scrapy.crawler import CrawlerProcess
c = CrawlerProcess({
'USER_AGENT': 'Mozilla/5.0',
# save in file CSV, JSON or XML
'FEED_FORMAT': 'csv', # csv, json, xml
'FEED_URI': 'output.csv', #
})
c.crawl(QuotesSpider)
c.start()
I built my first scray spider in several hours for the last two days but i am stuck right now - the main purpose i wanted to achieve is to extract all data to later filter it in csv. Now, the real crucial data for me (Companies without! webpages) is dropped because scrapy can't find the xpath i provided if an item has a homepage. I tried an if statement here, but its not working.
Example website: https://www.achern.de/de/Wirtschaft/Unternehmen-A-Z/Unternehmen?view=publish&item=company&id=1345
I use xPath selector: response.xpath("//div[#class='cCore_contactInformationBlockWithIcon cCore_wwwIcon']/a/#href").extract()
Example non-website: https://www.achern.de/de/Wirtschaft/Unternehmen-A-Z/Unternehmen?view=publish&item=company&id=1512
Spider Code:
# -*- coding: utf-8 -*-
import scrapy
class AchernSpider(scrapy.Spider):
name = 'achern'
allowed_domains = ['www.achern.de']
start_urls = ['https://www.achern.de/de/Wirtschaft/Unternehmen-A-Z/']
def parse(self, response):
for href in response.xpath("//ul[#class='cCore_list cCore_customList']/li[*][*]/a/#href"):
url = response.urljoin(href.extract())
yield scrapy.Request(url, callback= self.scrape)
def scrape(self, response):
#Extracting the content using css selectors
print("Processing:"+response.url)
firma = response.css('div>#cMpu_publish_company>h2.cCore_headline::text').extract()
anschrift = response.xpath("//div[contains(#class,'cCore_addressBlock_address')]/text()").extract()
tel = response.xpath("//div[#class='cCore_contactInformationBlockWithIcon cCore_phoneIcon']/text()").extract()
mail = response.xpath(".//div[#class='cCore_contactInformationBlock']//*[contains(text(), '#')]/text()").extract()
web1 = response.xpath("//div[#class='cCore_contactInformationBlockWithIcon cCore_wwwIcon']/a/#href").extract()
if "http:" not in web1:
web = "na"
else:
web = web1
row_data=zip(firma,anschrift,tel,mail,web1) #web1 must be changed to web but then it only give out "n" for every link
#Give the extracted content row wise
for item in row_data:
#create a dictionary to store the scraped info
scraped_info = {
'Firma' : item[0],
'Anschrift' : item[1] +' 77855 Achern',
'Telefon' : item[2],
'Mail' : item[3],
'Web' : item[4],
}
#yield or give the scraped info to scrapy
yield scraped_info
So overall it should export the DROPPED items even "web" is not there..
Hope someone can help, greetings S
Using
response.css(".cCore_wwwIcon > a::attr(href)").get()
gives you a None or the website address, then you can use or to provide a default:
website = response.css(".cCore_wwwIcon > a::attr(href)").get() or 'na'
Also, I refactored your scraper to use css selectors. Note that I've used .get() instead of .extract() to get a single item, not a list, which cleans up the code quite a bit.
import scrapy
from scrapy.crawler import CrawlerProcess
class AchernSpider(scrapy.Spider):
name = 'achern'
allowed_domains = ['www.achern.de']
start_urls = ['https://www.achern.de/de/Wirtschaft/Unternehmen-A-Z/']
def parse(self, response):
for url in response.css("[class*=cCore_listRow] > a::attr(href)").extract():
yield scrapy.Request(url, callback=self.scrape)
def scrape(self, response):
# Extracting the content using css selectors
firma = response.css('.cCore_headline::text').get()
anschrift = response.css('.cCore_addressBlock_address::text').get()
tel = response.css(".cCore_phoneIcon::text").get()
mail = response.css("[href^=mailto]::attr(href)").get().replace('mailto:', '')
website = response.css(".cCore_wwwIcon > a::attr(href)").get() or 'na'
scraped_info = {
'Firma': firma,
'Anschrift': anschrift + ' 77855 Achern',
'Telefon': tel,
'Mail': mail,
'Web': website,
}
yield scraped_info
if __name__ == "__main__":
p = CrawlerProcess()
p.crawl(AchernSpider)
p.start()
output:
with website:
{'Firma': 'Wölfinger Fahrschule GmbH', 'Anschrift': 'Güterhallenstraße 8 77855 Achern', 'Telefon': '07841 6738132', 'Mail': 'info#woelfinger-fahrschule.de', 'Web': 'http://www.woelfinger-fahrschule.de'}
without website:
{'Firma': 'Zappenduster-RC Steffen Liepe', 'Anschrift': 'Am Kirchweg 16 77855 Achern', 'Telefon': '07841 6844700', 'Mail': 'Zappenduster-Rc#hotmail.de', 'Web': 'na'}
In the first place, If I use extract_first, scrapy gives me the first element of each page and if I run it like this it returns all the content I want but in one-liners.
In Second place, I can't make scrapy go to the links I just scraped and get information from inside these links, returning an empty csv file.
from scrapy import Spider
from companies.items import CompaniesItem
import re
class companiesSpider(Spider):
name = "companies"
allowed_domains = ['http://startup.miami',]
# Defining the list of pages to scrape
start_urls = ["http://startup.miami/category/startups/page/" + str(1*i) + "/" for i in range(0, 10)]
def parse(self, response):
rows = response.xpath('//*[#id="datafetch"]')
for row in rows:
link = row.xpath('.//h2/a/#href').extract()
name = row.xpath('.//header/h2/a/text()').extract()
item = CompaniesItem()
item['link'] = link
item['name'] = name
yield item
Your parse-method is not yielding any requests or items. In the part below we go through the pages and get the urls & names. In the parse_detail you can add additional data to the item.
Instead of hardcoding to 10 pages we check if there is a next page, and go through the parse again if it's the case.
from scrapy import Spider
from ..items import CompaniesItem
import scrapy
class CompaniesSpider(Spider):
name = "companies"
allowed_domains = ['startup.miami']
# Defining the list of pages to scrape
start_urls = ["http://startup.miami/category/startups/"]
def parse(self, response):
# get link & name and send item to parse_detail in meta
rows = response.xpath('//*[#id="datafetch"]/article')
for row in rows:
link = row.xpath('.//#href').extract_first()
name = row.xpath(
'.//*[#class="textoCoworking"]/text()').extract_first()
item = CompaniesItem()
item['link'] = link
item['name'] = name.strip()
yield scrapy.Request(link,
callback=self.parse_detail,
meta={'item': item})
# get the next page
next_page = response.xpath(
'//*[#class="next page-numbers"]/#href').extract_first()
if next_page:
yield scrapy.Request(next_page, callback=self.parse)
def parse_detail(self, response):
item = response.meta['item']
# add other details to the item here
yield item
To put the results in a csv file you can launch the scraper like this: scrapy crawl companies -o test_companies.csv
CODE:
import scrapy
from scrapy.spiders import CrawlSpider
from scrapy import Request
class TestSpider(CrawlSpider):
name = "test_spyder"
allowed_domains = ["stackoverflow.com"]
start_urls = ['https://stackoverflow.com/tags']
def parse(self, response):
title_1 = response.xpath('//h1/text()').extract_first()
next_url = 'https://stackoverflow.com/users'
title_2 = Request(url=next_url, callback=self.parse_some)
yield {'title_1': title_1, 'title_2': title_2}
def parse_some(self, response):
return response.xpath('//h1/text()').extract_first()
I don't understand why instead second page title (Users) i get other value (https://stackoverflow.com/users>).
Scrapy should return next values: Tags + Users, but returns: Tag + <Request GET htt... at list i think so.
Where is the error and how to fix it?
To crawl url you need to yield a Request object. So your parse callbacks should either:
Yield a dictionary/Item - this is the end of crawl chain. The item is being generated, it is sent through pipelines and finally saved somewhere if you have that set up.
Yield a Request object - this still continues the crawl chain to another callback.
Example of this process:
crawl url1 (2)
crawl url2 (2)
yield item (1)
Your spider in this case should look like this:
def parse(self, response):
title = response.xpath('//h1/text()').extract_first()
yield {'title': title}
next_url = 'https://stackoverflow.com/users'
yield Request(url=next_url, callback=self.parse_some)
And your end results crawling with scrapy crawl spider -o output.json:
# output.json
[
{'title': 'title1'},
{'title': 'title2'}
]
I am trying to parse a site, an e-store. I parse a page with products, which are loaded with ajax, get urls of these products,and then parse additional info of each product following these parced urls.
My script gets the list of first 4 items on the page, their urls, makes the request, parses add info, but then not returning into the loop and so spider closes.
Could somebody help me in solving this? I'm pretty new to this kind of stuff, and ask here when totally stuck.
Here is my code:
from scrapy import Spider
from scrapy.selector import Selector
from scrapy.http.request import Request
from scrapy_sokos.items import SokosItem
class SokosSpider(Spider):
name = "sokos"
allowed_domains = ["sokos.fi"]
base_url = "http://www.sokos.fi/fi/SearchDisplay?searchTermScope=&searchType=&filterTerm=&orderBy=8&maxPrice=&showResultsPage=true&beginIndex=%s&langId=-11&sType=SimpleSearch&metaData=&pageSize=4&manufacturer=&resultCatEntryType=&catalogId=10051&pageView=image&searchTerm=&minPrice=&urlLangId=-11&categoryId=295401&storeId=10151"
start_urls = [
"http://www.sokos.fi/fi/SearchDisplay?searchTermScope=&searchType=&filterTerm=&orderBy=8&maxPrice=&showResultsPage=true&beginIndex=0&langId=-11&sType=SimpleSearch&metaData=&pageSize=4&manufacturer=&resultCatEntryType=&catalogId=10051&pageView=image&searchTerm=&minPrice=&urlLangId=-11&categoryId=295401&storeId=10151",
]
for i in range(0, 8, 4):
start_urls.append((base_url) % str(i))
def parse(self, response):
products = Selector(response).xpath('//div[#class="product-listing product-grid"]/article[#class="product product-thumbnail"]')
for product in products:
item = SokosItem()
item['url'] = product.xpath('//div[#class="content"]/a[#class="image"]/#href').extract()[0]
yield Request(url = item['url'], meta = {'item': item}, callback=self.parse_additional_info)
def parse_additional_info(self, response):
item = response.meta['item']
item['name'] = Selector(response).xpath('//h1[#class="productTitle"]/text()').extract()[0].strip()
item['description'] = Selector(response).xpath('//div[#id="kuvaus"]/p/text()').extract()[0]
euro = Selector(response).xpath('//strong[#class="special-price"]/span[#class="euros"]/text()').extract()[0]
cent = Selector(response).xpath('//strong[#class="special-price"]/span[#class="cents"]/text()').extract()[0]
item['price'] = '.'.join(euro + cent)
item['number'] = Selector(response).xpath('//#data-productid').extract()[0]
yield item
The AJAX requests you are simulating are caught by the Scrapy "duplicate url filter".
Set dont_filter to True when yielding a Request:
yield Request(url=item['url'],
meta={'item': item},
callback=self.parse_additional_info,
dont_filter=True)