1.新建文件run.py
from scrapy.cmdline import execute # tmall:爬蟲的名字 # pro=男裝為需要傳入的參數值 execute(['scrapy', 'crawl', 'tmall', '-a', 'pro=男裝', '--nolog']) # 下面是無參數用法 # execute(['scrapy', 'crawl', 'tmall', '--nolog'])
2.爬蟲.py中重寫init方法,傳入參數;(字典編碼以字符串形式拼接到url后邊)
# 倒入頭文件 (字典編碼后以參數形式拼接到url) from urllib.parse import urlencode class TmallSpider(scrapy.Spider): name = 'tmall' allowed_domains = ['tmall.com'] def __init__(self, pro=None, *args, **kwargs): super(TmallSpider, self).__init__(*args, **kwargs) self.params = { 'q': pro, 'total_Page': 1, 'jumpto': 1, } self.start_url = 'https://list.tmall.com/search_product.htm?' + urlencode(self.params) def start_requests(self): print('self.start_url:' + self.start_url) # yield scrapy.Request( # url=self.start_url, # callback=self.get_total_page, # dont_filter=True, # ) def get_total_page(self, response): pass