【菜鸟学Python】使用Scrapy框架爬取糗事百科

第一步：

创建项目

scrapy stratproject [name]

如 scrapy startproject choushibaike

第二步：

进入到项目的文件夹目录创建APP

scrapy gensider baike lovehhy.net

第三步：

配置baike.py文件

# -*- coding: utf-8 -*-
import scrapy
from ..items import ChoushibaikeItem


class BaikeSpider(scrapy.Spider):
    name = \'baike\'
    allowed_domains = [\'lovehhy.net\']
    start_urls = [\'http://www.lovehhy.net/joke/Detail/QSBK\']

    def parse(self, response):

        titles = response.xpath(\'//div[@class="cat_llb"]/h3/a/text()\').extract()
        contents = response.xpath(\'//div[@class="cat_llb"]/div[@id="endtext"]/text()\').extract()
        times = response.xpath(\'//div[@class="cat_llb"]/text()\').extract()

        title_list = []
        for title in titles:
            title_list.append(title)

        content_list = []
        for content in contents:
            content_list.append(content)

        time_list = []
        for time in times:
            time_list.append(time)

        item_lists = zip(title_list, content_list, time_list)
        for item_list in item_lists:
            item = ChoushibaikeItem()
            item[\'title\'] = item_list[0]
            item[\'content\'] = item_list[1]
            item[\'time\'] = item_list[2][0:22]
            item[\'click\'] = item_list[2][22:-1]
            yield item

        next_url = response.xpath(\'//a[text()="下一页>>"]/@href\').extract_first()
        url = response.urljoin(next_url)
        yield scrapy.Request(url=url, callback=self.parse)

第四步：

配置items.py文件

import scrapy

class ChoushibaikeItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    content = scrapy.Field()
    time = scrapy.Field()
    click = scrapy.Field()

第五步：

配置pipelines.py文件

import pymongo


class MongoPipeline(object):
    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get(\'MONGO_URI\'),
            mongo_db=crawler.settings.get(\'MONGO_DB\')
        )

    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):
        name = item.__class__.__name__
        self.db[name].insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()

第六步：

配置settings.py文件

# -*- coding: utf-8 -*-

# Scrapy settings for choushibaike project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = \'choushibaike\'

SPIDER_MODULES = [\'choushibaike.spiders\']
NEWSPIDER_MODULE = \'choushibaike.spiders\'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36\'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False


ITEM_PIPELINES = {
   # \'choushibaike.pipelines.ChoushibaikePipeline\': 300,
   \'choushibaike.pipelines.MongoPipeline\': 400,
}



MONGO_URI = \'mongodb://admin:123456@localhost/\'
MONGO_DB = \'choushibaike\'

 

第七步：

运行项目

scrapy crawl baike