思路
一、想要實現(xiàn)登錄豆瓣關(guān)鍵點
分析真實post地址 ----尋找它的formdata，如下圖,按瀏覽器的F12可以找到。
實戰(zhàn)操作
- 實現(xiàn)：模擬登錄豆瓣，驗證碼處理，登錄到個人主頁就算是success
- 數(shù)據(jù)：沒有抓取數(shù)據(jù)，此實戰(zhàn)主要是模擬登錄和處理驗證碼的學(xué)習(xí)。要是有需求要抓取數(shù)據(jù)，編寫相關(guān)的抓取規(guī)則即可抓取內(nèi)容。
登錄成功展示如圖：
spiders文件夾中DouBan.py主要代碼如下：
# -*- coding: utf-8 -*-
import scrapy,urllib,re
from scrapy.http import Request,FormRequest
import ruokuai
'''
遇到不懂的問題？Python學(xué)習(xí)交流群：821460695滿足你的需求，資料都已經(jīng)上傳群文件，可以自行下載！
'''
class DoubanSpider(scrapy.Spider):
name = "DouBan"
allowed_domains = ["douban.com"]
#start_urls = ['http://douban.com/']
header={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36"} #供登錄模擬使用
def start_requests(self):
url='https://www.douban.com/accounts/login'
return [Request(url=url,meta={"cookiejar":1},callback=self.parse)]#可以傳遞一個標(biāo)示符來使用多個。如meta={'cookiejar': 1}這句，后面那個1就是標(biāo)示符
def parse(self, response):
captcha=response.xpath('//*[@id="captcha_image"]/@src').extract() #獲取驗證碼圖片的鏈接
print captcha
if len(captcha)>0:
'''此時有驗證碼'''
#人工輸入驗證碼
#urllib.urlretrieve(captcha[0],filename="C:/Users/pujinxiao/Desktop/learn/douban20170405/douban/douban/spiders/captcha.png")
#captcha_value=raw_input('查看captcha.png,有驗證碼請輸入:')
#用快若打碼平臺處理驗證碼--------驗證碼是任意長度字母，成功率較低
captcha_value=ruokuai.get_captcha(captcha[0])
reg=r'
(.*?)
'
reg=re.compile(reg)
captcha_value=re.findall(reg,captcha_value)[0]
print '驗證碼為：',captcha_value
data={
"form_email": "weisuen007@163.com",
"form_password": "weijc7789",
"captcha-solution": captcha_value,
#"redir": "https://www.douban.com/people/151968962/", #設(shè)置需要轉(zhuǎn)向的網(wǎng)址，由于我們需要爬取個人中心頁，所以轉(zhuǎn)向個人中心頁
}
else:
'''此時沒有驗證碼'''
print '無驗證碼'
data={
"form_email": "weisuen007@163.com",
"form_password": "weijc7789",
#"redir": "https://www.douban.com/people/151968962/",
}
print '正在登陸中......'
####FormRequest.from_response()進行登陸
return [
FormRequest.from_response(
response,
meta={"cookiejar":response.meta["cookiejar"]},
headers=self.header,
formdata=data,
callback=self.get_content,
)
]
def get_content(self,response):
title=response.xpath('//title/text()').extract()[0]
if u'登錄豆瓣' in title:
print '登錄失敗，請重試！'
else:
print '登錄成功'
'''
可以繼續(xù)后續(xù)的爬取工作
'''
ruokaui.py代碼如下：
我所用的是若塊打碼平臺，選擇url識別驗證碼，直接給打碼平臺驗證碼圖片的鏈接地址，傳回驗證碼的值。
# -*- coding: utf-8 -*-
import sys, hashlib, os, random, urllib, urllib2
from datetime import *
'''
遇到不懂的問題？Python學(xué)習(xí)交流群：821460695滿足你的需求，資料都已經(jīng)上傳群文件，可以自行下載！
'''
class APIClient(object):
def http_request(self, url, paramDict):
post_content = ''
for key in paramDict:
post_content = post_content + '%s=%s&'%(key,paramDict[key])
post_content = post_content[0:-1]
#print post_content
req = urllib2.Request(url, data=post_content)
req.add_header('Content-Type', 'application/x-www-form-urlencoded')
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor())
response = opener.open(req, post_content)
return response.read()
def http_upload_image(self, url, paramKeys, paramDict, filebytes):
timestr = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
boundary = '------------' + hashlib.md5(timestr).hexdigest().lower()
boundarystr = '\r\n--%s\r\n'%(boundary)
bs = b''
for key in paramKeys:
bs = bs + boundarystr.encode('ascii')
param = "Content-Disposition: form-data; name=\"%s\"\r\n\r\n%s"%(key, paramDict[key])
#print param
bs = bs + param.encode('utf8')
bs = bs + boundarystr.encode('ascii')
header = 'Content-Disposition: form-data; name=\"image\"; filename=\"%s\"\r\nContent-Type: image/gif\r\n\r\n'%('sample')
bs = bs + header.encode('utf8')
bs = bs + filebytes
tailer = '\r\n--%s--\r\n'%(boundary)
bs = bs + tailer.encode('ascii')
import requests
headers = {'Content-Type':'multipart/form-data; boundary=%s'%boundary,
'Connection':'Keep-Alive',
'Expect':'100-continue',
}
response = requests.post(url, params='', data=bs, headers=headers)
return response.text
def arguments_to_dict(args):
argDict = {}
if args is None:
return argDict
count = len(args)
if count <= 1:
print 'exit:need arguments.'
return argDict
for i in [1,count-1]:
pair = args[i].split('=')
if len(pair) < 2:
continue
else:
argDict[pair[0]] = pair[1]
return argDict
def get_captcha(image_url):
client = APIClient()
while 1:
paramDict = {}
result = ''
act = raw_input('請輸入打碼方式url:')
if cmp(act, 'info') == 0:
paramDict['username'] = raw_input('username:')
paramDict['password'] = raw_input('password:')
result = client.http_request('http://api.ruokuai.com/info.xml', paramDict)
elif cmp(act, 'register') == 0:
paramDict['username'] = raw_input('username:')
paramDict['password'] = raw_input('password:')
paramDict['email'] = raw_input('email:')
result = client.http_request('http://api.ruokuai.com/register.xml', paramDict)
elif cmp(act, 'recharge') == 0:
paramDict['username'] = raw_input('username:')
paramDict['id'] = raw_input('id:')
paramDict['password'] = raw_input('password:')
result = client.http_request('http://api.ruokuai.com/recharge.xml', paramDict)
elif cmp(act, 'url') == 0:
paramDict['username'] = '********'
paramDict['password'] = '********'
paramDict['typeid'] = '2000'
paramDict['timeout'] = '90'
paramDict['softid'] = '76693'
paramDict['softkey'] = 'ec2b5b2a576840619bc885a47a025ef6'
paramDict['imageurl'] = image_url
result = client.http_request('http://api.ruokuai.com/create.xml', paramDict)
elif cmp(act, 'report') == 0:
paramDict['username'] = raw_input('username:')
paramDict['password'] = raw_input('password:')
paramDict['id'] = raw_input('id:')
result = client.http_request('http://api.ruokuai.com/create.xml', paramDict)
elif cmp(act, 'upload') == 0:
paramDict['username'] = '********'
paramDict['password'] = '********'
paramDict['typeid'] = '2000'
paramDict['timeout'] = '90'
paramDict['softid'] = '76693'
paramDict['softkey'] = 'ec2b5b2a576840619bc885a47a025ef6'
paramKeys = ['username',
'password',
'typeid',
'timeout',
'softid',
'softkey'
]
from PIL import Image
imagePath = raw_input('Image Path:')
img = Image.open(imagePath)
if img is None:
print 'get file error!'
continue
img.save("upload.gif", format="gif")
filebytes = open("upload.gif", "rb").read()
result = client.http_upload_image("http://api.ruokuai.com/create.xml", paramKeys, paramDict, filebytes)
elif cmp(act, 'help') == 0:
print 'info'
print 'register'
print 'recharge'
print 'url'
print 'report'
print 'upload'
print 'help'
print 'exit'
elif cmp(act, 'exit') == 0:
break
return result
以上就是本文的全部內(nèi)容，希望對大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。
更多文章、技術(shù)交流、商務(wù)合作、聯(lián)系博主
微信掃碼或搜索：z360901061
微信掃一掃加我為好友
QQ號聯(lián)系： 360901061
您的支持是博主寫作最大的動力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點擊下面給點支持吧，站長非常感激您！手機微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點擊微信右上角掃一掃功能，選擇支付二維碼完成支付。
【本文對您有幫助就好】元
