How do I ignore pdf links while scraping using Scrapy? - python

I'm new to Scrapy and I'm currently making a spider that extracts only the event title and event description from a website. I am able to get the title and description, however, the spider is also trying to extract data from a pdf link which causes a "raise NotSupported("Response content isn't text")" error. How can I prevent the spider from doing this?
Here is my code:
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
class EventsspiderSpider(CrawlSpider):
name = 'eventsspider'
allowed_domains =['cs.acadiau.ca']
start_urls = ['https://cs.acadiau.ca/news-events/event-reader/using-dna-to-reverse-engineer-your-family-tree.html']
rules = (
Rule(LinkExtractor(allow=('news-events/event-reader/using-dna-to-reverse-engineer-your-family-tree.html', )), callback='parse_item', follow=True),)
def parse_item(self, response):
i = {}
title_list = response.xpath('//*[#id="event-items-15421"]/div[2]/div/h1/text()').extract()
data_list = response.xpath('//*[#id="event-items-15421"]/div[2]/div/div[1]/p[7]/span/text()').extract()
for x in range(0, len(title_list)):
i['title'] = title_list[x]
i['data'] = data_list[x]
yield i

Related

How to use Scrapy for URL crawling

I want to crawl the link https://www.aparat.com/.
I crawl it correctly and get all the video links with header tag;like this :
import scrapy
class BlogSpider(scrapy.Spider):
name = 'aparatspider'
start_urls = ['https://www.aparat.com/']
def parse(self, response):
print '=' * 80 , 'latest-trend :'
ul5 = response.css('.block-grid.xsmall-block-grid-2.small-block-grid-3.medium-block-grid-4.large-block-grid-5.is-not-center')
ul5 = ul5.css('ul').css('li')
latesttrend = []
for li5 in ul5:
latesttrend.append(li5.xpath('div/div[1]/a').xpath('#onmousedown').extract_first().encode('utf8'))
print(latesttrend)
now my question is this:
How can I get all the links from the داغ ترین ها tag, more than 1000? Currently, I get only 60, more or less.
I did this with the following code :
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from scrapy.http import Request
class aparat_hotnewsItem(scrapy.Item):
videourl = scrapy.Field()
class aparat_hotnewsSpider(CrawlSpider):
name = 'aparat_hotnews'
allowed_domains = ['www.aparat.com']
start_urls = ['http://www.aparat.com/']
# Xpath for selecting links to follow
xp = 'your xpath'
rules = (
Rule(LinkExtractor(restrict_xpaths=xp), callback='parse_item', follow=True),
)
def parse_item(self, response):
item = aparat_hotnewsItem()
item['videourl'] = response.xpath('your xpath').extract()
yield item

Regular Expression for website

http://www.bbc.com/news/business-41097280
Is the website I want the regular expression for.
So far, I am using the following, where
'.+\/news\/business[-.]\d{8}$
Which is part of this code segment here, used with Scrapy
from scrapy.item import Item, Field
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
class TryItem(Item):
url = Field()
class BbchrcrawlerSpider(CrawlSpider):
name = "bbchrcrawler"
allowed_domains = ["www.bbc.com"]
start_urls = ['http://www.bbc.com/news/business-']
rules = (Rule(LinkExtractor(allow=['.+\/news\/business+\-d{8}$']), callback='parse_item', follow=True),)
def parse_item(self, response):
Item = TryItem()
Item['url'] = response.url
yield Item
What's the correct way to get the URL there for extracting multiple pages with the same format?
The result should collect URLs with the following format:
bbc.com/news/business-########
You can try this:
pattern = "bbc\.com/news/business-\d+"
rules = (Rule(LinkExtractor(allow=[pattern]), callback='parse_item', follow=True),)

Scrapy neither shows any error nor fetches any data

Tried to parse product name and price from a site using scrapy. However, When i run my scrapy code it neither shows any error nor fetches any data. What I'm doing wrong is beyond my capability to find out. Hope there is someone to take a look into it.
"items.py" includes:
import scrapy
class SephoraItem(scrapy.Item):
Name = scrapy.Field()
Price = scrapy.Field()
spider file named "sephorasp.py" contains:
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
class SephoraspSpider(CrawlSpider):
name = "sephorasp"
allowed_domains = ['sephora.ae']
start_urls = ["https://www.sephora.ae/en/stores/"]
rules = [
Rule(LinkExtractor(restrict_xpaths='//li[#class="level0 nav-1 active first touch-dd parent"]')),
Rule(LinkExtractor(restrict_xpaths='//li[#class="level2 nav-1-1-1 active first"]'),
callback="parse_item")
]
def parse_item(self, response):
page = response.xpath('//div[#class="product-info"]')
for titles in page:
Product = titles.xpath('.//a[#title]/text()').extract()
Rate = titles.xpath('.//span[#class="price"]/text()').extract()
yield {'Name':Product,'Price':Rate}
Here is the Link to the Log:
"https://www.dropbox.com/s/8xktgh7lvj4uhbh/output.log?dl=0"
It works when I play around with BaseSpider:
from scrapy.spider import BaseSpider
from scrapy.http.request import Request
class SephoraspSpider(BaseSpider):
name = "sephorasp"
allowed_domains = ['sephora.ae']
start_urls = [
"https://www.sephora.ae/en/travel-size/make-up",
"https://www.sephora.ae/en/perfume/women-perfume",
"https://www.sephora.ae/en/makeup/eye/eyeshadow",
"https://www.sephora.ae/en/skincare/moisturizers",
"https://www.sephora.ae/en/gifts/palettes"
]
def pro(self, response):
item_links = response.xpath('//a[contains(#class,"level0")]/#href').extract()
for a in item_links:
yield Request(a, callback = self.end)
def end(self, response):
item_link = response.xpath('//a[#class="level2"]/#href').extract()
for b in item_link:
yield Request(b, callback = self.parse)
def parse(self, response):
page = response.xpath('//div[#class="product-info"]')
for titles in page:
Product= titles.xpath('.//a[#title]/text()').extract()
Rate= titles.xpath('.//span[#class="price"]/text()').extract()
yield {'Name':Product,'Price':Rate}
Your xpaths are heavily flawed.
Rule(LinkExtractor(restrict_xpaths='//li[#class="level0 nav-1 active first touch-dd parent"]')),
Rule(LinkExtractor(restrict_xpaths='//li[#class="level2 nav-1-1-1 active first"]'),
You are matching whole class ranges which can change at any point and the order might be different in scrapy. Just pick one class, it's most likely unique enough:
Rule(LinkExtractor(restrict_xpaths='//li[contains(#class,"level0")]')),
Rule(LinkExtractor(restrict_xpaths='//li[contains(#class,"level2")]')),

scrapy spider code check

so im' trying to scrape the website in the SgmlLinkExtractor parameters below website with scrapy, and this is what my spider looks like:
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from desidime_sample.items import DesidimeItem
import string
class DesidimeSpider(CrawlSpider):
name = "desidime"
allowed_domains = ["desidime.com"]
start_urls = ["http://www.desidime.com/forums/hot-deals-online"]
rules = (
Rule(SgmlLinkExtractor(allow=(), restrict_xpaths=('''//td[not(#*)]/div
[not(#*)]/a[not(#class)]/#href''')), callback="parse_items", follow=True),
)
def parse_items(self, response):
hxs = HtmlXPathSelector(response)
deals = hxs.select('''//div[#class='user-comment-text'][1]''')
items = []
for deals in deals:
item = DesidimeItem()
item["deal"] = deals.select("//div[#class='user-comment-text'][1]/p/text()").extract()
item["link"] = deals.select("//div[#class='user-comment-text'][1]/p[1]/a[1]/#href").extract()
items.append(item)
return items
It should be quite obvious what I'm trying to do, but for some reason when I tell the spider to crawl and export the text and links to the CVS file, I end up with:
link,deal http://wwww.facebook.com/desidime,
http://wwww.facebook.com/desidime,
(same thing for many more lines, then:)
",,"
, " same url" ,
(same thing for many more lines, then:)
"link,deals"
So, can anyone tell me what the problem is? If you run each of my above xpaths as reponse.xpath("xpath").extract() after scrapy shell "//corresponingcrawlruleurl", you'll get the right results.
The problem is inside the parse_items callback. When you iterate over the deals, the deal context-specific locators have to be relative. In other words, start your XPath expressions inside the loop with a dot:
def parse_items(self, response):
for deal in response.xpath("//div[#class='user-comment-text'][1]"):
item = DesidimeItem()
item["deal"] = deal.xpath(".//p/text()").extract()
item["link"] = deal.xpath(".//p[1]/a[1]/#href").extract()
yield item
(note that I've also simplified the code).
Here is the complete spider, I'm executing (it does scrape the text and links, though I don't know what is your desired output):
import scrapy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
class DesidimeItem(scrapy.Item):
deal = scrapy.Field()
link = scrapy.Field()
class DesidimeSpider(CrawlSpider):
name = "desidime"
allowed_domains = ["desidime.com"]
start_urls = ["http://www.desidime.com/forums/hot-deals-online"]
rules = [
Rule(LinkExtractor(restrict_xpaths="//td[not(#*)]/div[not(#*)]/a[not(#class)]"),
callback="parse_items",
follow=True),
]
def parse_items(self, response):
for deal in response.xpath("//div[#class='user-comment-text'][1]"):
item = DesidimeItem()
item["deal"] = deal.xpath(".//p/text()").extract()
item["link"] = deal.xpath(".//p[1]/a[1]/#href").extract()
yield item

How to recursively crawl whole website using scrapy

I want to crawl complete website using scrapy but right now its only crawling single page
import scrapy
from scrapy.http import HtmlResponse
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from scrapy.contrib.exporter import JsonItemExporter
class IzodspiderSpider(scrapy.Spider):
name = 'izodspider'
allowed_domains = ['izod.com']
start_urls = ['http://izod.com/']
rules = [Rule(SgmlLinkExtractor(), callback='parse_item', follow=True)]
def parse(self, response):
hxs = scrapy.Selector(response)
meta = hxs.xpath('//meta[#name=\'description\']/#content').extract()
name = hxs.xpath('//div[#id=\'product-details\']/h5').extract()
desc = hxs.xpath('//div[#id=\'product-details\']/p').extract()
is there any way to extract meta tags using portia ?
There is an error in the rule definition and inside the callback.
Since the parse function you use is parse_item you have to call it inside the callback instead of parse
You can find more information about the callback function on the documentation here http://doc.scrapy.org/en/latest/topics/request-response.html?highlight=callback#topics-request-response-ref-request-callback-arguments
class IzodspiderSpider(CrawlSpider):
name = "izod"
depth_limit= 0
bot_name = 'izod'
allowed_domains = ['izod.com']
start_urls = ['http://www.izod.com']
rules = (
Rule(SgmlLinkExtractor(allow=('')), callback='parse_items',follow= True),
)
def parse_items(self, response):
hxs = scrapy.Selector(response)
meta = hxs.xpath('//meta[#name=\'description\']/#content').extract()
name = hxs.xpath('//div[#id=\'product-details\']/h5').extract()
desc = hxs.xpath('//div[#id=\'product-details\']/p').extract()

Categories