本案例中主要讲述三种不同方式的scrapy框架模拟用户登陆方式。
- 人人网案例-采用传统cookies设置方式进行模拟登陆。
- post表单请求方式（自行定位表单位置）
- post方式调用scrapy.FormRequest.from_response函数进行自动定位表单方式进行模拟登陆.
1.案例框架结构
2.案例模拟登陆界面以及cookies获取界面
3.三种爬虫文件
# -*- coding: utf-8 -*-
import scrapy
import re
class RenrenSpider(scrapy.Spider):
name = 'renren'
allowed_domains = ['renren.com']
start_urls = ['http://www.renren.com/970254374/profile']
def start_requests(self):
cookies = "输入cookies"
cookies = {i.split("=")[0]:i.split("=")[1] for i in cookies.split("; ")}#cookies字符串转化为字典
yield scrapy.Request(
self.start_urls[0],
callback=self.parse,
cookies=cookies
)
def parse(self, response):
print(re.findall("物是人非", response.body.decode()))#如果能够输出用户名说明请求成功了
yield scrapy.Request(
"http://www.renren.com/970254374/profile?v=info_timeline",#以后的请求都会带上cookies
callback=self.parse_detail
)
def parse_detail(self, response):
print(re.findall("物是人非", response.body.decode()))
# -*- coding: utf-8 -*-
import scrapy
import re
class GithubSpider(scrapy.Spider):
name = 'github'
allowed_domains = ['github.com']
start_urls = ['http://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="***",
password="***",
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("login.html", "w", encoding="utf-8") as f:
f.write(response.body.decode())
print(re.findall("songjianguo12", response.body.decode()))
# -*- coding: utf-8 -*-
import scrapy
import re
class Github2Spider(scrapy.Spider):
name = 'github2'
allowed_domains = ['github.com']
start_urls = ['http://github.com/login']
def parse(self, response):
yield scrapy.FormRequest.from_response(
response, #自动的从rsponse中寻找from表单-自动定位表单
formdata = {"login":"***", "password":"***"},
callback = self.after_login,
)
def after_login(self, response):
print(re.findall("songjianguo12", response.body.decode()))
4.settings.py文件
# -*- coding: utf-8 -*-
# Scrapy settings for login project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'login'
SPIDER_MODULES = ['login.spiders']
NEWSPIDER_MODULE = 'login.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
# USER_AGENTS = [ "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5" ]
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = "WARNING"
COOKIES_DEBUG = True #查看cookies发送方向
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'login.middlewares.LoginSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'login.middlewares.LoginDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'login.pipelines.LoginPipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
- 本案例不进行效果展示，请读者自行实验效果，案例完全可行，如遇到问题无法结局可以给我留言，我看到会立即回复。