Created
May 5, 2016 15:03
-
-
Save rdesfo/44fda923f75fca4b050f73a1b210a20c to your computer and use it in GitHub Desktop.
scrapy bath restaurants
This file contains 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 | |
class TripadvisorSpider(scrapy.Spider): | |
name = 'tripadvisor' | |
allow_domains = ['tripadvisor.com'] | |
start_urls = [ | |
'http://www.tripadvisor.com/Restaurants-g40505-Bath_Maine.html' | |
] | |
custom_settings = { | |
'FEED_EXPORT_FIELDS': ["name", "rating", "latitude", "longitude", "url"] | |
} | |
def parse(self, response): | |
urls = response.xpath('//h3[@class="title"]/a/@href').extract() | |
for url in urls: | |
absolute_url = response.urljoin(url) | |
# yield {'Url': absolute_url} | |
yield scrapy.Request(absolute_url, callback=self.parse_restaurant) | |
# next page | |
next_page_url = response.xpath('//a[text()="Next"]/@href').extract_first() | |
next_absolute_url = response.urljoin(next_page_url) | |
request = scrapy.Request(next_absolute_url, callback=self.parse) | |
yield request | |
def parse_restaurant(self, response): | |
rating = response.xpath('//img[@property="ratingValue"]/@content').extract() | |
name = response.xpath('//div[@class="mapContainer"]/@data-name').extract() | |
latitude = response.xpath('//div[@class="mapContainer"]/@data-lat').extract() | |
longitude = response.xpath('//div[@class="mapContainer"]/@data-lng').extract() | |
url = response.url | |
yield { 'name': name | |
, 'rating': rating | |
, 'latitude': latitude | |
, 'longitude': longitude | |
, 'url': url | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment