aykhans/PostScrape
1
0
Fork 0
mirror of https://github.com/aykhans/PostScrape.git synced 2025-04-21 00:07:16 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

added first_page

Browse Source
This commit is contained in:
ayxan 2022-09-07 00:55:01 +04:00
parent bc3caf3b51
commit 10ee472243
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/post_scrape/spiders/car_spider.py
View File

@ -6,11 +6,12 @@ class ToScrapeCSSSpider(scrapy.Spider):
headers = { headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36' 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
} }
last_page = 1 first_page = 1
last_page = 2
def start_requests(self): def start_requests(self):
urls = [ urls = [
'https://turbo.az/autos', f'https://turbo.az/autos?page={self.first_page}',
] ]
for url in urls: for url in urls:
@ -23,7 +24,7 @@ class ToScrapeCSSSpider(scrapy.Spider):
yield response.follow(f"https://turbo.az{p.get()}", callback=self.parse_detail_url, headers=self.headers) yield response.follow(f"https://turbo.az{p.get()}", callback=self.parse_detail_url, headers=self.headers)
next_page = response.xpath('//a[@rel="next"]/@href').get() next_page = response.xpath('//a[@rel="next"]/@href').get()
if next_page is not None and int(next_page[next_page.rfind('=')+1:]) <= self.last_page: if next_page is not None and int(next_page[next_page.rfind('=')+1:]) < self.last_page:
yield response.follow(f"https://turbo.az{next_page}", callback=self.parse, headers=self.headers) yield response.follow(f"https://turbo.az{next_page}", callback=self.parse, headers=self.headers)
def parse_detail_url(self, r): def parse_detail_url(self, r):