爬虫pearPro

本项目中介绍

1. 使用了selenium，需要添加匹配的chromedriver.exe的路径在webdriver.Chrome(executable_path='path')
2. 请求视频详情页 如：https://www.pearvideo.com/video_1708124 , xpath 解析、获取其下的.mp4播放地址时，需要用slelenium动态加载
3. 下载了https://www.pearvideo.com/category_5 板块中 生活：LIFE 下的 最热 中的四个视频
4. mp4播放地址url 类似：https://video.pearvideo.com/mp4/third/20201120/cont-1708124-15454898-191438-hd.mp4
5. 访问视频详情页，获取video的mp4文件的url,然后下载到本地目录当中

项目结构

mypearPro
    mypearPro
        spiders
            pear.py
        items.py
        middlewares.py
        pipelines.py
        settings.py

pear.py中

# -*- coding: utf-8 -*-
import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import random
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver import ActionChains
import json, re
import requests
import os


class PearSpider(scrapy.Spider):
    name = 'pear'
    allowed_domains = ['pearvideo.com']
    start_urls = ['https://www.pearvideo.com/category_5']
    path = os.path.dirname(os.path.abspath('__file__'))
    download_path = os.path.join(path, 'video')

    def __init__(self):
        chrome_options = Options()
        chrome_options.add_argument('--window-size=1500,1366')
        self.bro = webdriver.Chrome(options=chrome_options,
                                    executable_path='D:python_charm爬虫课件我的项目文件夹chromedriver.exe')

    def parse(self, response):
        li_lists = response.xpath('//*[@id="listvideoListUl"]/li')
        for li in li_lists:
            title = li.xpath('./div/a/div[2]/text()').extract_first()
            print('-----> 视频的标题是：', title)
            new_url = 'https://www.pearvideo.com/'+li.xpath('./div/a/@href').extract_first()
            print('-----> 视频的详情url是：', new_url)
            yield scrapy.Request(new_url, callback=self.parse_video)
        # video = response.xpath('//*[@id="JprismPlayer"]/video/@src').extract_first()

    # 访问视频详情页，获取video的mp4
    def parse_video(self, response):
        video = response.xpath('//*[@id="JprismPlayer"]/video/@src').extract_first()
        print('-----> video的地址是：', video)
        yield scrapy.Request(video, callback=self.parse_mp4)

    def parse_mp4(self, response):
        name = response.url.split('/')[-1]
        print('-----> 下载的存储的地址1为：',self.path)
        print('-----> 下载的存储的地址2为:', self.download_path)
        with open(os.path.join(self.download_path, name), 'wb') as f:
            f.write(response.body)

    def closed(self, spider):
        self.bro.quit()

items.py

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

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

import scrapy


class MypearproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    url = scrapy.Field()

middlewares.py

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

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

from scrapy import signals
from scrapy.http import HtmlResponse
from time import sleep


class MypearproSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class MypearproDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        bro = spider.bro
        if 'video_' in request.url:
            bro.get(request.url)
            sleep(2)
            page_text = bro.page_source
            new_response = HtmlResponse(url=request.url,body=page_text,encoding='utf-8',request=request)
            return new_response
        else:
            return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

pipelines.py

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

# 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


class MypearproPipeline:
    def process_item(self, item, spider):
        return item

settings.py

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

# Scrapy settings for myPearPro 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 = 'myPearPro'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = 'ERROR'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# 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 = 3
# 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 = {
#    'myPearPro.middlewares.MypearproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    'myPearPro.middlewares.MypearproDownloaderMiddleware': 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 = {
#    'myPearPro.pipelines.MypearproPipeline': 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'