Here's my code
import scrapy
class PvSpider(scrapy.Spider):
name = 'pv'
allowed_domains = ['www.piaov.com']
start_urls = ['http://www.piaov.com/']
def start_requests(self):
yield scrapy.Request(url='http://www.piaov.com/list/7.html')
def parse(self, response):
names = response.xpath("//ul[#class='mlist']//li/a/#title").extract()
on = response.meta.get("names", [])
cmp_names = on + names
for p in range(2, 7):
yield scrapy.Request(url='http://www.piaov.com/list/7_{}.html'.format(p),
meta={"names": cmp_names},
callback=self.parse)
yield scrapy.Request("http://www.piaov.com", meta={"names": cmp_names}, callback=self.parse_item)
def parse_item(self, response):
pass
When i debug my code in 'parse_item' function,the 'response.meta["names"]' only include the first page datas(12 titles in this case), how could i get the 6 pages datas list.
Its because you have URL http://www.piaov.com and scrapy ignores the duplicate URLs unless dont_filter=True is specified in Request like Request(url_here, dont_filter=True)
Also I don't like your logic of scraper, why are you calling parse_item at all? it is not necessary. Please see the code below and do it like that.
import scrapy
class PvSpider(scrapy.Spider):
name = 'pv'
allowed_domains = ['www.piaov.com']
start_urls = ['http://www.piaov.com/']
def start_requests(self):
yield scrapy.Request(url='http://www.piaov.com/list/7.html')
def parse(self, response):
for name in response.xpath("//ul[#class='mlist']//li/a/#title").extract():
yield {"name": name}
for p in range(2, 7):
yield scrapy.Request(url='http://www.piaov.com/list/7_{}.html'.format(p),
callback=self.parse)
Related
I'm in reach of a personal milestone with scrapy. The aim is to properly understand the callback and cb_kwargs, I've read the documentation countless times but I learn best with visual code, practice and an explanation.
I have an example scraper, the aim is to grab the book name, price and go into each book page and extract a single piece of information. I'm trying to understand how to properly get information on the next few pages also, which I know is dependent on understanding the operation of callbacks.
When I run my script It returns results only for the first page, how do I get the additional pages?
Here's my scraper:
class BooksItem(scrapy.Item):
items = Field(output_processor = TakeFirst())
price = Field(output_processor = TakeFirst())
availability = Field(output_processor = TakeFirst())
class BookSpider(scrapy.Spider):
name = "books"
start_urls = ['https://books.toscrape.com']
def start_request(self):
for url in self.start_url:
yield scrapy.Request(
url,
callback = self.parse)
def parse(self, response):
data = response.xpath('//div[#class = "col-sm-8 col-md-9"]')
for books in data:
loader = ItemLoader(BooksItem(), selector = books)
loader.add_xpath('items','.//article[#class="product_pod"]/h3/a//text()')
loader.add_xpath('price','.//p[#class="price_color"]//text()')
for url in [books.xpath('.//a//#href').get()]:
yield scrapy.Request(
response.urljoin(url),
callback = self.parse_book,
cb_kwargs = {'loader':loader})
for next_page in [response.xpath('.//div/ul[#class="pager"]/li[#class="next"]/a//#href').get()]:
if next_page is not None:
yield response.follow(next_page, callback=self.parse)
def parse_book(self, response, loader):
book_quote = response.xpath('//p[#class="instock availability"]//text()').get()
loader.add_value('availability', book_quote)
yield loader.load_item()
I believe the issue is with the part where I try to grab the next few pages. I have tried an alternative approach using the following:
def start_request(self):
for url in self.start_url:
yield scrapy.Request(
url,
callback = self.parse,
cb_kwargs = {'page_count':0}
)
def parse(self, response, next_page):
if page_count > 3:
return
...
...
page_count += 1
for next_page in [response.xpath('.//div/ul[#class="pager"]/li[#class="next"]/a//#href').get()]:
yield response.follow(next_page, callback=self.parse, cb_kwargs = {'page_count': page_count})
However, I get the following error with this approach:
TypeError: parse() missing 1 required positional argument: 'page_cntr'
It should be start_requests, and self.start_urls (inside the function).
get() will return the first result, what you want is getall() in order to return a list.
There is no need for a for loop for the "next_page" part, it's not a mistake just unnecessary.
In the line for url in books.xpath you're getting every url twice, again not a mistake but still...
Here data = response.xpath('//div[#class = "col-sm-8 col-md-9"]') you don't select the books one by one, you select the whole books container, you can check that len(data.getall()) == 1.
book_quote = response.xpath('//p[#class="instock availability"]//text()').get() will return \n, look at the source at try to find out why (hint: 'i' tag).
Compare your code to this and see what I changed:
import scrapy
from scrapy import Field
from scrapy.loader import ItemLoader
from scrapy.loader.processors import TakeFirst
class BooksItem(scrapy.Item):
items = Field(output_processor=TakeFirst())
price = Field(output_processor=TakeFirst())
availability = Field(output_processor=TakeFirst())
class BookSpider(scrapy.Spider):
name = "books"
start_urls = ['https://books.toscrape.com']
def start_requests(self):
for url in self.start_urls:
yield scrapy.Request(
url,
callback=self.parse)
def parse(self, response):
data = response.xpath('//div[#class = "col-sm-8 col-md-9"]//li')
for books in data:
loader = ItemLoader(BooksItem(), selector=books)
loader.add_xpath('items', './/article[#class="product_pod"]/h3/a//text()')
loader.add_xpath('price', './/p[#class="price_color"]//text()')
for url in books.xpath('.//h3/a//#href').getall():
yield scrapy.Request(
response.urljoin(url),
callback=self.parse_book,
cb_kwargs={'loader': loader})
next_page = response.xpath('.//div/ul[#class="pager"]/li[#class="next"]/a//#href').get()
if next_page:
yield response.follow(next_page, callback=self.parse)
def parse_book(self, response, loader):
# option 1:
book_quote = response.xpath('//p[#class="instock availability"]/i/following-sibling::text()').get().strip()
# option 2:
# book_quote = ''.join(response.xpath('//div[contains(#class, "product_main")]//p[#class="instock availability"]//text()').getall()).strip()
loader.add_value('availability', book_quote)
yield loader.load_item()
From this webpage I am trying to get that kind of link where different products are located. There are 6 categories having More info button which when I traverse recursively, I usually reach the target pages. This is one such product listings page I wish to get.
Please note that some of these pages have both product listing and more info buttons, which is why I failed to capture the product listing pages accurately.
Current spider looks like the following (fails to grab lots of product listings pages):
import scrapy
class NorgrenSpider(scrapy.Spider):
name = 'norgren'
start_urls = ['https://www.norgren.com/de/en/list']
def start_requests(self):
for start_url in self.start_urls:
yield scrapy.Request(start_url, callback=self.parse)
def parse(self, response):
link_list = []
for item in response.css(".match-height a.more-info::attr(href)").getall():
if not "/detail/" in item:
inner_page_link = response.urljoin(item)
link_list.append(inner_page_link)
yield {"target_url":inner_page_link}
for new_link in link_list:
yield scrapy.Request(new_link, callback=self.parse)
Expected output (randomly taken):
https://www.norgren.com/de/en/list/directional-control-valves/in-line-and-manifold-valves
https://www.norgren.com/de/en/list/pressure-switches/electro-mechanical-pressure-switches
https://www.norgren.com/de/en/list/pressure-switches/electronic-pressure-switches
https://www.norgren.com/de/en/list/directional-control-valves/sub-base-valves
https://www.norgren.com/de/en/list/directional-control-valves/non-return-valves
https://www.norgren.com/de/en/list/directional-control-valves/valve-islands
https://www.norgren.com/de/en/list/air-preparation/combination-units-frl
How to get all the product listings pages from the six categories?
import scrapy
class NorgrenSpider(scrapy.Spider):
name = 'norgren'
start_urls = ['https://www.norgren.com/de/en/list']
def start_requests(self):
for start_url in self.start_urls:
yield scrapy.Request(start_url)
def parse(self, response):
# check if there are items in the page
if response.xpath('//div[contains(#class, "item-list")]//div[#class="buttons"]/div[#class="more-information"]/a/#href'):
yield scrapy.Request(url=response.url, callback=self.get_links, dont_filter=True)
# follow "more info" buttons
for url in response.xpath('//a[text()="More info"]/#href').getall():
yield response.follow(url)
def get_links(self, response):
yield {"target_url": response.url}
next_page = response.xpath('//a[#class="next-button"]/#href').get()
if next_page:
yield response.follow(url=next_page, callback=self.get_links)
Maybe filter only pages that have at least one link to details? Here is an example of how to identify if a page meets the criteria you are searching for:
import scrapy
class NorgrenSpider(scrapy.Spider):
name = 'norgren'
start_urls = ['https://www.norgren.com/de/en/list']
def start_requests(self):
for start_url in self.start_urls:
yield scrapy.Request(start_url, callback=self.parse)
def parse(self, response):
link_list = []
more_info_items = response.css(
".match-height a.more-info::attr(href)").getall()
detail_items = [item for item in more_info_items if '/detail/' in item]
if len(detail_items) > 0:
print(f'This is a link you are searching for: {response.url}')
for item in more_info_items:
if not "/detail/" in item:
inner_page_link = response.urljoin(item)
link_list.append(inner_page_link)
yield {"target_url": inner_page_link}
for new_link in link_list:
yield scrapy.Request(new_link, callback=self.parse)
I only printed the link to the console, but you can figure out how to log it to where you need.
Hi I would like to scrape 2 different domain in my script I have tried my if statement but I it seems that it is not working, any idea please?
Here's my code
class SalesitemSpiderSpider(scrapy.Spider):
name = 'salesitem_spider'
allowed_domains = ['www2.hm.com']
start_urls = [
'https://www2.hm.com/en_us/sale/shopbyproductladies/view-all.html?sort=stock&image-size=small&image=stillLife&offset=0&page-size=9999',
'https://www.forever21.com/us/shop/catalog/category/f21/sale',
]
def parse_start_url(response):
if (response.url == 'https://www2.hm.com/en_us/sale/shopbyproductladies/view-all.html?sort=stock&image-size=small&image=stillLife&offset=0&page-size=9999'):
parse_1(response)
if (response.url == 'https://www.forever21.com/us/shop/catalog/category/f21/sale'):
parse_2(response)
def parse_1(self, response):
for product_item in response.css('li.product-item'):
item = {
'title': product_item.css('h3.item-heading a.link::text').extract_first(),
'regular-price': product_item.css('strong.item-price span.price.regular::text').extract_first(),
'sale-price': product_item.css('strong.item-price span.price.sale::text').extract_first(),
'photo-url': product_item.css('.image-container img::attr(data-src)').extract_first(),
'description-url': "https://www2.hm.com/" + product_item.css('h3.item-heading a::attr(href)').extract_first(),
}
yield item
def parse_2(self, response):
#Some code getting item on domain 2
Please Help thank you
Check your allowed_domains variable. You should add new domain, like ['www2.hm.com', 'forever21.com'] or remove it at all. Also you have no parse function.
I can suppose to remove your start_urls with if and use start_requests instead. Your code will be more readable.
import scrapy
class SalesitemSpiderSpider(scrapy.Spider):
name = 'salesitem_spider'
allowed_domains = ['www2.hm.com', 'forever21.com']
def start_requests(self):
urls = (
(self.parse_1, 'https://www2.hm.com/en_us/sale/shopbyproductladies/view-all.html?sort=stock&image-size=small&image=stillLife&offset=0&page-size=9999'),
(self.parse_2, 'https://www.forever21.com/us/shop/catalog/category/f21/sale'),
)
for cb, url in urls:
yield scrapy.Request(url, callback=cb)
def parse_1(self, response):
print 111111111
def parse_2(self, response):
print 2222222222
I need to scrape all of the items but only 1 item is scrape.
My code is working fine before but when I transfer it to other project which is same code this happens I don't know why
I need to get all of the items according to the page size in start_url
here's my working code
class HmSalesitemSpider(scrapy.Spider):
name = 'HM_salesitem'
allowed_domains = ['www2.hm.com']
start_urls = ['https://www2.hm.com/en_us/sale/shopbyproductladies/view-
all.html?sort=stock&image-size=small&image=stillLife&offset=0&page-
size=3002']
def parse(self, response):
for product_item in response.css('li.product-item'):
url = "https://www2.hm.com/" + product_item.css('a::attr(href)').extract_first()
yield scrapy.Request(url=url, callback=self.parse_subpage)
def parse_subpage(self, response):
item = {
'title': response.xpath("normalize-space(.//h1[contains(#class, 'primary') and contains(#class, 'product-item-headline')]/text())").extract_first(),
'sale-price': response.xpath("normalize-space(.//span[#class='price-value']/text())").extract_first(),
'regular-price': response.xpath('//script[contains(text(), "whitePrice")]/text()').re_first("'whitePrice'\s?:\s?'([^']+)'"),
'photo-url': response.css('div.product-detail-main-image-container img::attr(src)').extract_first(),
'description': response.css('p.pdp-description-text::text').extract_first()
}
yield item
Please Help. Thank you
It seems you have problem with indents. Move yielding request to for loop:
def parse(self, response):
for product_item in response.css('li.product-item'):
url = "https://www2.hm.com/" + product_item.css('a::attr(href)').get()
yield scrapy.Request(url=url, callback=self.parse_subpage)
Or this is a bit cleared version:
def parse(self, response):
for link in response.css('li.product-item a::attr(href)').extract():
yield response.follow(link, self.parse_subpage)
I'm trying to use scrapy to crawl some page with a lot of links inside, but my existing code so far only show the contents of the first link.
What mistake have I made?
from scrapy.spiders import BaseSpider
from scrapy.spiders import Spider
from scrapy.http.request import Request
from scrapy.selector import Selector
from Proje.items import ProjeItem
class ProjeSpider(BaseSpider):
name = "someweb"
allowed_domains = ["someweb.com"]
start_urls = [
"http://someweb.com/indeks/"
]
def parse(self, response):
for sel in response.xpath('//ul[#id="indeks-container"]'):
for tete in sel.xpath('//linkkk').re('//linkkk.*?(?=")'):
links = 'http:'+str(tete)
req = Request(links,callback=self.kontene)
return req
def kontene(self, response):
for mbuh in response.xpath('//head'):
Item = ProjeItem()
Item['title'] = mbuh.xpath('//title/text()').extract()
yield Item
according to the scrapy docs, parse needs to return an interable of Request, i.e. a list or a generator. Just change return to yield and it should work as expected:
def parse(self, response):
for sel in response.xpath('//ul[#id="indeks-container"]'):
for tete in sel.xpath('//linkkk').re('//linkkk.*?(?=")'):
links = 'http:'+str(tete)
req = Request(links,callback=self.kontene)
yield req
The issue is that you have a return statement within your for loop. In Python, a return will return out of the function, giving you only the first links worth of content. Instead, consider adding req to a list of returned objects.
def parse(self, response):
req_list = []
for sel in response.xpath('//ul[#id="indeks-container"]'):
for tete in sel.xpath('//linkkk').re('//linkkk.*?(?=")'):
links = 'http:'+str(tete)
req = Request(links,callback=self.kontene)
req_list += req
return req_list