Scratch program learning

douban.py

scrapy genspider douban movie.douban.com
scrapy genspider taobao www.taobao.com

import scrapy
from scrapy import Selector, Request
from scrapy.http import HtmlResponse

from spider2107.items import MovieItem


class DoubanSpider(scrapy.Spider):
    name = 'douban'
    allowed_domains = ['movie.douban.com']

    def start_requests(self):
        for page in range(10):
            yield Request(url=f'https://movie.douban.com/top250?start={
      page * 25}&filter=')

    def parse(self, response: HtmlResponse):
        sel = Selector(response)
        lis = sel.css('#content > div > div.article > ol > li')
        for li in lis:  # type:Selector
            movie_item = MovieItem()
            movie_item['title'] = li.css('span.title::text').extract_first()
            movie_item['rank'] = li.css('span.rating_num::text').extract_first()
            movie_item['subject'] = li.css('span.inq::text').extract_first()
            yield movie_item

items.py

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class MovieItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    rank = scrapy.Field()
    subject = scrapy.Field()

settings.py

# Scrapy settings for spider2107 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 = 'spider2107'

SPIDER_MODULES = ['spider2107.spiders']
NEWSPIDER_MODULE = 'spider2107.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 2

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 2
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
# COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
# TELNETCONSOLE_ENABLED = False

# Override the default request headers:
# DEFAULT_REQUEST_HEADERS = {
    
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
# }

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
    
# 'spider2107.middlewares.Spider2107SpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
    
# 'spider2107.middlewares.Spider2107DownloaderMiddleware': 543,
# }

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
# EXTENSIONS = {
    
# 'scrapy.extensions.telnet.TelnetConsole': None,
# }

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    
    'spider2107.pipelines.DbPipeline': 200,
    'spider2107.pipelines.Spider2107Pipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
# AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
# HTTPCACHE_ENABLED = True
# HTTPCACHE_EXPIRATION_SECS = 0
# HTTPCACHE_DIR = 'httpcache'
# HTTPCACHE_IGNORE_HTTP_CODES = []
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

Save method

scrapy crawl douban -o douban.json
scrapy crawl douban -o douban.scv
scrapy crawl douban -o douban.xml
pip freeze ( Query dependency list )

pipelines.py

# Define your item pipelines here
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# useful for handling different item types with a single interface
import openpyxl
import pymysql


class DbPipeline:
    def __init__(self):
        self.conn = pymysql.connect(host='localhost', port=3306,
                                    user='root', password='Abc123!!',
                                    database='hrs', charset='utf8mb4')
        self.cursor = self.conn.cursor()

    def close_spider(self, spider):
        self.conn.commit()
        self.conn.close()

    def process_item(self, item, spider):
        title = item.get('title', '')
        rank = item.get('rank', 0)
        subject = item.get('subject', '')
        self.cursor.execute(
            'insert into tb_movie (title ,rating, subject)'
            'values (%s, %s,%s)',
            (title, rank, subject)
        )
        return item


class Spider2107Pipeline:
    def __init__(self):
        self.wb = openpyxl.Workbook()
        self.ws = self.wb.active
        self.ws.title = 'Top250'
        self.ws.append((' title ', ' score ', ' The theme '))

    def close_spider(self, spider):
        self.wb.save(' Movie data .xlsx')

    def process_item(self, item, spider):
        title = item.get('title', '')
        rank = item.get('rank', '')
        subject = item.get('subject', '')
        self.ws.append((title, rank, subject))
        return item

        

Save method

scrapy crawl douban