python爬虫框架talonspider简单介绍

import time
from talonspider import Item, TextField, AttrField
from pprint import pprint

class TestSpider(Item):
  title = TextField(css_select='.book-info>h1>em')
  author = TextField(css_select='a.writer')
  cover = AttrField(css_select='a#bookImg>img', attr='src')

  def tal_title(self, title):
    return title

  def tal_cover(self, cover):
    return 'http:' + cover

if __name__ == '__main__':
  item_data = TestSpider.get_item(url='http://book.qidian.com/info/1004608738')
  pprint(item_data)

from talonspider import Item, TextField, AttrField
from pprint import pprint

# 定义继承自item的爬虫类
class DoubanSpider(Item):
  target_item = TextField(css_select='div.item')
  title = TextField(css_select='span.title')
  cover = AttrField(css_select='div.pic>a>img', attr='src')
  abstract = TextField(css_select='span.inq')

  def tal_title(self, title):
    if isinstance(title, str):
      return title
    else:
      return ''.join([i.text.strip().replace('\xa0', '') for i in title])

if __name__ == '__main__':
  items_data = DoubanSpider.get_items(url='https://movie.douban.com/top250')
  result = []
  for item in items_data:
    result.append({
      'title': item.title,
      'cover': item.cover,
      'abstract': item.abstract,
    })
  pprint(result)

# !/usr/bin/env python
from talonspider import Spider, Item, TextField, AttrField, Request
from talonspider.utils import get_random_user_agent


# 定义继承自item的爬虫类
class DoubanItem(Item):
  target_item = TextField(css_select='div.item')
  title = TextField(css_select='span.title')
  cover = AttrField(css_select='div.pic>a>img', attr='src')
  abstract = TextField(css_select='span.inq')

  def tal_title(self, title):
    if isinstance(title, str):
      return title
    else:
      return ''.join([i.text.strip().replace('\xa0', '') for i in title])


class DoubanSpider(Spider):
  # 定义起始url，必须
  start_urls = ['https://movie.douban.com/top250']
  # requests配置
  request_config = {
    'RETRIES': 3,
    'DELAY': 0,
    'TIMEOUT': 20
  }
  # 解析函数 必须有
  def parse(self, html):
    # 将html转化为etree
    etree = self.e_html(html)
    # 提取目标值生成新的url
    pages = [i.get('href') for i in etree.cssselect('.paginator>a')]
    pages.insert(0, '"User-Agent": get_random_user_agent()
    }
    for page in pages:
      url = self.start_urls[0] + page
      yield Request(url, request_config=self.request_config, headers=headers, callback=self.parse_item)

  def parse_item(self, html):
    items_data = DoubanItem.get_items(html=html)
    # result = []
    for item in items_data:
      # result.append({
      #   'title': item.title,
      #   'cover': item.cover,
      #   'abstract': item.abstract,
      # })
      # 保存
      with open('douban250.txt', 'a+') as f:
        f.writelines(item.title + '\n')


if __name__ == '__main__':
  DoubanSpider.start()

/Users/howie/anaconda3/envs/work3/bin/python /Users/howie/Documents/programming/python/git/talonspider/examples/douban_page_by_spider.py
2017-06-07 23:17:30,346 - talonspider - INFO: talonspider started
2017-06-07 23:17:30,693 - talonspider_requests - INFO: GET a url: https://movie.douban.com/top250
2017-06-07 23:17:31,074 - talonspider_requests - INFO: GET a url: https://movie.douban.com/top250"_blank" href="https://github.com/howie6879/talonspider/blob/master/examples/douban_page_by_spider.py">douban_page_by_spider.py。

3.说明
学习之作，待完善的地方还有很多，欢迎提意见，项目地址talonspider。