def start_request(self):
url = f'https://maoyan.com/board/4'
yield scrapy.request(url=url,callback=self.parse)
def start_request(self):
url = ''
yield scrapy.request(url=url,callback=self.parse)
def start_request(self):
url = f'https://maoyan.com/board/4'
yield scrapy.request(url=url)
def start_requests(self):
yield scrapy.request()
def parse(self, response):
for row in etree.HTML(response.body).xpath("//table[@class='DataGrid']//tr")[1:]:
sec_page = start_urls[0] + ''.join(row.xpath("td/a/@href"))
yield scrapy.request(sec_page, callback=self.sec_parse)
# -*- coding: utf-8 -*-
import scrapy
from movies.Item import MaoyanspidersItem
import xlml.etree
from bs4 import BeautifulSoup as bs
class MoviesSpider(scrapy.Spider):
name = 'movies'
allowed_domains = ['maoyan.com']
start_urls = ['http://maoyan.com/']
# def parse(self, response):
# pass
def start_request(self):
for i
url = f'https://maoyan.com/'
yield scrapy.request(url=url,callback=self.parse)
def parse(self, response):
soup = bs(response.text,'html.parser')
print(response.text)
