我编写了一个脚本来从网站获取数据。由于@href是重定向链接,因此我在收集网站URL时遇到问题。如何将重定向URL转换为重定向到的实际网站?
import scrapy
import logging
class AppSpider(scrapy.Spider):
name = 'app'
allowed_domains = ['www.houzz.in']
start_urls = ['https://www.houzz.in/professionals/searchDirectory?topicId=26721&query=Design-Build+Firms&location=Mumbai+City+District%2C+India&distance=100&sort=4']
def parse(self, response):
lists = response.xpath('//li[@class="hz-pro-search-results__item"]/div/div[@class="hz-pro-search-result__info"]/div/div/div/a')
for data in lists:
link = data.xpath('.//@href').get()
yield scrapy.Request(url=link, callback=self.parse_houses, meta={'Links': link})
next_page = response.xpath('(//a[@class="hz-pagination-link hz-pagination-link--next"])[1]/@href').extract_first()
if next_page:
yield response.follow(response.urljoin(next_page), callback=self.parse)
def parse_houses(self, response):
link = response.request.meta['Links']
firm_name = response.xpath('//div[@class="hz-profile-header__title"]/h1/text()').get()
name = response.xpath('//div[@class="profile-meta__val"]/text()').get()
phone = response.xpath('//div[@class="hz-profile-header__contact-info text-right mrm"]/a/span/text()').get()
website = response.xpath('(//div[@class="hz-profile-header__contact-info text-right mrm"]/a)[2]/@href').get()
yield {
'Links': link,
'Firm_name': firm_name,
'Name': name,
'Phone': phone,
'Website': website
}
您可以这样做:
class AppSpider(scrapy.Spider):
base_url = 'www.houzz.in{}'
.
.
.
def foo(self):
actual_url = self.base_url.format(redirect_url)
您必须向该目标URL发出请求,以查看其指向的位置
在您的情况下,您可以简单地执行HEAD
请求,该请求不会加载目标URL的任何正文,因此也可以节省带宽并提高脚本速度]]
class AppSpider(scrapy.Spider):
name = 'app'
allowed_domains = ['www.houzz.in']
start_urls = ['https://www.houzz.in/professionals/searchDirectory?topicId=26721&query=Design-Build+Firms&location=Mumbai+City+District%2C+India&distance=100&sort=4']
def parse(self, response):
lists = response.xpath('//li[@class="hz-pro-search-results__item"]/div/div[@class="hz-pro-search-result__info"]/div/div/div/a')
for data in lists:
link = data.xpath('.//@href').get()
yield scrapy.Request(url=link, callback=self.parse_houses, meta={'Links': link})
next_page = response.xpath('(//a[@class="hz-pagination-link hz-pagination-link--next"])[1]/@href').extract_first()
if next_page:
yield response.follow(response.urljoin(next_page), callback=self.parse)
def parse_houses(self, response):
link = response.request.meta['Links']
firm_name = response.xpath('//div[@class="hz-profile-header__title"]/h1/text()').get()
name = response.xpath('//div[@class="profile-meta__val"]/text()').get()
phone = response.xpath('//div[@class="hz-profile-header__contact-info text-right mrm"]/a/span/text()').get()
website = response.xpath('(//div[@class="hz-profile-header__contact-info text-right mrm"]/a)[2]/@href').get()
yield Request(url=website,
method="HEAD",
callback=self.get_final_link,
meta={'data':
{
'Links': link,
'Firm_name': firm_name,
'Name': name,
'Phone': phone,
'Website': website
}
}
)
def get_final_link(self, response):
data = response.meta['data']
data['website'] = response.headers['Location']
yield data