Yêu cầu dịch vụ

Web Scraping với Python

Thomas Laetsch

Data Scientist, NYU

Ôn lại Spider

import scrapy
from scrapy.crawler import CrawlerProcess

class SpiderClassName(scrapy.Spider):
    name = "spider_name"
    # the code for your spider
    ...

process = CrawlerProcess()

process.crawl(SpiderClassName)

process.start()

Ôn lại Spider

class DCspider( scrapy.Spider ):
    name = "dc_spider"

    def start_requests( self ):
        urls = [ 'https://www.datacamp.com/courses/all' ]
        for url in urls:
            yield scrapy.Request( url = url, callback = self.parse )

    def parse( self, response ):
        # simple example: write out the html
        html_file = 'DC_courses.html'
        with open( html_file, 'wb' ) as fout:
            fout.write( response.body )

Tóm tắt về start_requests

def start_requests( self ):

    urls = ['https://www.datacamp.com/courses/all']

    for url in urls:
        yield scrapy.Request( url = url, callback = self.parse )

def start_requests( self ):
    url = 'https://www.datacamp.com/courses/all'
    yield scrapy.Request( url = url, callback = self.parse )

Ở đây, scrapy.Request sẽ tạo biến response cho ta
Tham số url chỉ trang cần thu thập
Tham số callback chỉ nơi gửi biến response để xử lý

Nhìn tổng quan

class DCspider( scrapy.Spider ):
    name = "dc_spider"

    def start_requests( self ):
        urls = [ 'https://www.datacamp.com/courses/all' ]
        for url in urls:
            yield scrapy.Request( url = url, callback = self.parse )

    def parse( self, response ):
        # simple example: write out the html
        html_file = 'DC_courses.html'
        with open( html_file, 'wb' ) as fout:
            fout.write( response.body )

Kết thúc yêu cầu

Web Scraping với Python