python之scrapy模拟登陆人人网

1、settings.py主要配置信息，包括USER_AGENT等

# -*- coding: utf-8 -*-

# Scrapy settings for renren 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 = 'renren'

SPIDER_MODULES = ['renren.spiders']
NEWSPIDER_MODULE = 'renren.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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 = {
#    'renren.middlewares.RenrenSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'renren.middlewares.RenrenDownloaderMiddleware': 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 = {
#    'renren.pipelines.RenrenPipeline': 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'

View Code

2、rr.py，主要模拟登陆

# -*- coding: utf-8 -*-
import scrapy
import time
import re
class RrSpider(scrapy.Spider):
    name = 'rr'
    allowed_domains = ['renren.com']
    start_urls = ['http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201961933877']

    def start_requests(self):
        base_url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp='
        s = time.strftime("%S")
        ms = int(round(time.time() % (int(time.time())), 3) * 1000)
        date_time = '20188010' + str(s) + str(ms)
        login_url = base_url + date_time
        data = {'email': '18620028487',
                'icode': '',
                'origURL': 'http://www.renren.com/home',
                'domain': 'renren.com',
                'key_id': '1',
                'captcha_type': 'web_login',
                'password': '41980c8f91e2c872910598a9e0a147d05934506893ef022c5b42357a67e0a3be',
                'rkey': 'fc9dfa5a27bed56e61f122d80f2f401d',
                'f':'http%3A%2F%2Fwww.renren.com%2FLogin.do%3Frf%3Dr%26origURL%3Dhttp%253A%252F%252Fwww.renren.com%252F971298880%252Fprofile'
                   }
        yield scrapy.FormRequest(url=login_url, formdata=data, callback=self.parse_login, dont_filter=True)

    def parse_login(self, response):
        yield scrapy.Request(url='http://www.renren.com/971298880/profile', callback=self.parse_text, dont_filter=True)

    def parse_text(self, response):
        print(response.body.decode())

 3、登陆信息