最近在学习scrapy框架中写爬虫，被坑爹的空格键和tab键给害惨了。上代码：

错误代码：

import scrapy
import re


class GithubSpider(scrapy.Spider):
    name = 'Github'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
        post_data = dict(
                login="noobpythoner",
                password="zhoudawei123",
                authenticity_token=authenticity_token,
                utf8=utf8,
                commit=commit
        )
        yield scrapy.FormRequest(
            "https: //  github.com  /   session",
            formdata=post_data,
            callback=self.after_login
        )

    def after_login(self, response):
        # with open("./a.html", "wb", encoding="utf-8") as file:
        #     file.write(response.body.decode())
        print(re.findall("noobpythoner|NoobPythoner", response.body.decode()))
        # print(response.body.decode())

上述代码错误之处在于： scrapy.FormRequest()函数的第一个参数，这是直接从浏览器复制过来的Url地址，正是由于url地址中的空格导致了请求不成功，返回结果没有任何数据：

正确的代码：

import scrapy
import re


class GithubSpider(scrapy.Spider):
    name = 'Github'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
        post_data = dict(
                login="noobpythoner",
                password="zhoudawei123",
                authenticity_token=authenticity_token,
                utf8=utf8,
                commit=commit
        )
        yield scrapy.FormRequest(
            "https://github.com/session",
            formdata=post_data,
            callback=self.after_login
        )

    def after_login(self, response):
        # with open("./a.html", "wb", encoding="utf-8") as file:
        #     file.write(response.body.decode())
        print(re.findall("noobpythoner|NoobPythoner", response.body.decode()))
        # print(response.body.decode())

这下输出结果如下：