# -*- coding: utf-8 -*-
import scrapy

class TiebaSpider(scrapy.Spider):
  name = 'tieba' # 貼吧爬蟲
  allowed_domains = ['tieba.baidu.com'] # 允許爬取的范圍
  start_urls = [] # 爬蟲起始地址

  # 命令格式： scrapy crawl tieba -a tiebaName=放置奇兵 -a pn=250
  def __init__(self, tiebaName=None, pn=None, *args, **kwargs):
    print('< 貼吧名稱 >： ' + tiebaName)
    super(eval(self.__class__.__name__), self).__init__(*args, **kwargs)
    self.start_urls = ['https://tieba.baidu.com/f?kw=%s&ie=utf-8&pn=%s' % (tiebaName,pn)]

  def parse(self, response):
    print(response.request.url) # 結果：https://tieba.baidu.com/f?kw=%E6%94%BE%E7%BD%AE%E5%A5%87%E5%85%B5&ie=utf-8&pn=250

# 指定 Scrapy 命令存放目錄
COMMANDS_MODULE = 'baidu_tieba.commands'

import scrapy.commands.crawl as crawl
from scrapy.exceptions import UsageError
from scrapy.commands import ScrapyCommand


class Command(crawl.Command):

  def add_options(self, parser):
    # 為命令添加選項
    ScrapyCommand.add_options(self, parser)
    parser.add_option("-k", "--keyword", type="str", dest="keyword", default="",
             help="set the tieba's name you want to crawl")
    parser.add_option("-p", "--pageNum", type="int", action="store", dest="pageNum", default=0,
             help="set the page number you want to crawl")

  def process_options(self, args, opts):
    # 處理從命令行中傳入的選項參數(shù)
    ScrapyCommand.process_options(self, args, opts)
    if opts.keyword:
      tiebaName = opts.keyword.strip()
      if tiebaName != '':
        self.settings.set('TIEBA_NAME', tiebaName, priority='cmdline')
    else:
      raise UsageError("U must specify the tieba's name to crawl,use -kw TIEBA_NAME!")
    self.settings.set('PAGE_NUM', opts.pageNum, priority='cmdline')

  def run(self, args, opts):
    # 啟動爬蟲
    self.crawler_process.crawl('tieba')
    self.crawler_process.start()

# -*- coding: utf-8 -*-
import json

class BaiduTiebaPipeline(object):

  @classmethod
  def from_settings(cls, settings):
    return cls(settings)

  def __init__(self, settings):
    self.settings = settings

  def open_spider(self, spider):
    # 開啟爬蟲
    spider.start_urls = [
      'https://tieba.baidu.com/f?kw=%s&ie=utf-8&pn=%s' % (self.settings['TIEBA_NAME'], self.settings['PAGE_NUM'])]

  def close_spider(self, spider):
    # 關閉爬蟲
    pass

  def process_item(self, item, spider):
    # 將帖子內(nèi)容保存到文件
    with open('tieba.txt', 'a', encoding='utf-8') as f:
      json.dump(dict(item), f, ensure_ascii=False, indent=2)
    return item

ITEM_PIPELINES = {
  'baidu_tieba.pipelines.BaiduTiebaPipeline': 50,
}

scrapy run -k 放置奇兵 -p 250