Python scrapy.cmdline 模块，execute() 实例源码

def cmd():
    cmdline.execute("scrapy crawl zol".split())

def main():
    Spider_name = AutoHome_WOM_Spider.settings.STAR_SPIDER_NAME
    star_spider = "scrapy crawl %s" %(Spider_name)
    cmdline.execute(star_spider.split())

def quotesbot_spider_scheduler():
    os.system('scrapy crawl author')
    # cmdline.execute("scrapy crawl author".split())

def parse_page(self, response):
        soup = BeautifulSoup(response.body, 'html.parser', from_encoding='utf-8')
        movie_name_tag = soup.find('div', id='content').findChild('h1')
        no = soup.find('span', 'top250-no').get_text()
        movie_name = movie_name_tag.findChildren()[0].get_text() + movie_name_tag.findChildren()[1].get_text()
        director = soup.find('a', rel='v:directedBy').get_text()
        #TODO ?????????BS
        writer = soup.find('span', text='??').next_sibling.next_sibling.text
        actor = '/'.join(star.text for star in soup.findAll('a', rel='v:starring'))
        type = '/'.join(genre.text for genre in soup.findAll('span', property='v:genre'))
        region = soup.find('span', text='????/??:').next_sibling
        language = soup.find('span', text='??:').next_sibling
        date = soup.find('span', property='v:initialReleaseDate').text
        length_tag = soup.find('span', property='v:runtime')
        if str(length_tag.next_sibling) != '<br/>':
            length = length_tag.text + str(length_tag.next_sibling)
        else:
            length = length_tag.text
        another_name = soup.find('span', text='??:').next_sibling
        introduction = soup.find('span', property='v:summary').text
        grade = soup.find('strong', property='v:average').text
        comment_times = soup.find('span', property='v:votes').text

        item = DoubanMovieItem()
        item['no'] = no
        item['movie_name'] = movie_name
        item['director'] = director
        item['writer'] = writer
        item['actor'] = actor
        item['type'] = type
        item['region'] = region
        item['language'] = language
        item['date'] = date
        item['length'] = length
        item['another_name'] = another_name
        item['introduction'] = introduction
        item['grade'] = grade
        item['comment_times'] = comment_times

        return item
# if __name__ == '__main__':
#     execute('scrapy crawl douban_movie'.split(' '))