学习笔记CB005:关键词、语料提取

# coding:utf-8

import sys

import importlib

importlib.reload(sys)

import pynlpir

pynlpir.open()

s = '怎么才能把电脑里的垃圾文件删除'

key_words = pynlpir.get_key_words(s, weighted=True)

for key_word in key_words:

    print(key_word[0], 't', key_word[1])

pynlpir.close()

# coding:utf-8

import sys

import importlib

importlib.reload(sys)

import scrapy

class BaiduSearchSpider(scrapy.Spider):

    name = "baidu_search"

    allowed_domains = ["baidu.com"]

    start_urls = [

            "https://www.baidu.com/s?wd=电脑 垃圾 文件 删除"

    ]

    def parse(self, response):

        filename = "result.html"

        with open(filename, 'wb') as f:

            f.write(response.body)

# coding:utf-8

import sys

import importlib

importlib.reload(sys)

import scrapy

from scrapy.utils.markup import remove_tags

class BaiduSearchSpider(scrapy.Spider):

    name = "baidu_search"

    allowed_domains = ["baidu.com"]

    start_urls = [

            "https://www.baidu.com/s?wd=电脑 垃圾 文件 删除"

    ]

    def parse(self, response):

        # filename = "result.html"

        # with open(filename, 'wb') as f:

        #     f.write(response.body)

        hrefs = response.selector.xpath('//div[contains(@class, "c-container")]/h3/a/@href').extract()

        # for href in hrefs:

        #     print(href)

        #     yield scrapy.Request(href, callback=self.parse_url)

        containers = response.selector.xpath('//div[contains(@class, "c-container")]')

        for container in containers:

            href = container.xpath('h3/a/@href').extract()[0]

            title = remove_tags(container.xpath('h3/a').extract()[0])

            c_abstract = container.xpath('div/div/div[contains(@class, "c-abstract")]').extract()

            abstract = ""

            if len(c_abstract) > 0:

                abstract = remove_tags(c_abstract[0])

            request = scrapy.Request(href, callback=self.parse_url)

            request.meta['title'] = title

            request.meta['abstract'] = abstract

            yield request

    def parse_url(self, response):

        print(len(response.body))

        print("url:", response.url)

        print("title:", response.meta['title'])

        print("abstract:", response.meta['abstract'])

        content = remove_tags(response.selector.xpath('//body').extract()[0])

        print("content_len:", len(content))