wxpath定位-采集验证-入库-使用。
from scrapy.spider import Spider from scrapy.crawler import CrawlerProcess class EnglishName(Spider): name = ‘EnglishName‘ start_urls = [‘http://babynames.net/all/starts-with/%(first)s?page=%(page)i‘ % {‘first‘: first, ‘page‘: page,} for first in ‘abcdefghijklmnopqrstuvwxyz‘ for page in range(1, 30, 1)] def parse(self, response): for wname in response.xpath(".//ul[@class=‘names-results listing-view‘]/li"): grab_url = response.url print grab_url wboy = wname.xpath("a/span[@class=‘result-gender boy‘]") wgirl = wname.xpath("a/span[@class=‘result-gender girl‘]") wres = wname.xpath("a/span[@class=‘result-name‘]/text()").extract() isboy = 1 if wboy == []: isboy = 0 for w in wres: wres=w print isboy print wres if __name__ == ‘__main__‘: process = CrawlerProcess({‘DOWNLOAD_DELAY‘:2, ‘CONCURRENT_REQUESTS_PER_DOMAIN‘: 6, ‘USER_AGENT‘:‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2950.5 Safari/537.36‘ }) process.crawl(EnglishName) process.start()
时间: 2024-10-18 06:16:07