python知乎爬虫，模拟登录，自动保存获取答案

python环境：python3.X

依赖的包：requests

下载文件到某个文件夹，然后运行，根据提示执行程序

下载，显示验证码：

class ZhiHu():

_session=None

favor_data=100

def __init__(self):

self.do_first()

def get_captcha(self):

return _captcha_url+str(int(time.time()*1000))+_captcha_url_end

def show_or_save_captcha(self,url):

global _session

r=_session.get(url,headers=header_data,verify=True)

with open("code.gif",'wb') as f:

f.write(r.content)

#显示验证码

try:

print("haha")

im = Image.open("code.gif")

im.show()

except:

print("请打开下载的验证码文件code.gif")

登录：

def input_data(self):

global email

global password

global question_url

self.username=raw_input('请输入用户名:')

self.password=raw_input('请输入密码:')

self.show_or_save_captcha(self.get_captcha())

self.captcha=raw_input('请输入验证码:')

下载某个问题下的高赞答案，存储在一个txt文件中：

def get_answer_text(self,url,answers=15):

global _session

global favor_data

r=_session.get(url,headers=header_data,verify=True)

pat=re.compile('"count">[s]*?(.*?)')

_list=re.findall(pat,r.text)

#print(_list);

#favor_list=[int(k) for k in _list]

favor_list=[]

#下面主要是将以“K”为单位的赞同数转化为数字

for i in _list:

if 'K' in i:

#print('k in'+i)

i = i.replace('K','000')

favor_list.append(int(i))

else:

#print(i)

favor_list.append(int(i))

favor_list.sort(reverse=True)

if len(favor_list)>=answers:

favor_data=favor_list[answers-1]

else:

favor_data=0

self.save_text(r)

下载某个问题下的答案中的所有图片，并且按照回答人的昵称归类

def get_answer_img(self,url):

global _session

r=_session.get(url,headers=header_data,verify=True).text

item_pattern=re.compile('

')

img_pattern=re.compile('

pattern_title=re.compile('([sS]*?)')

#author_pattern=re.compile('

author_pattern=re.compile('

([Ss]*?)

')

items=re.findall(item_pattern,r)

title=re.findall(pattern_title,r)

authors=[]

img_list=[]

i=0

try :

for item in items:

i+=1

authors.append(re.findall(author_pattern,item))

img_list.append(re.findall(img_pattern,item))

except :

print('查找出了一点问题')

traceback.print_exc()

try:

#print(authors)

j=0

for author in authors:

img_urls=img_list[j]

#print(len(img_urls))

if len(img_urls) == 0:

continue

title_text=title[0];

author_text=''

if len(author)>0:

author_text=author[0]

path=self.createPathIfNotExist(title_text+'\'+author[0])

j+=1

k=0

for url in img_urls:

if 'https' not in url:

#print('坏图：'+url)

continue

print(url)

temp=url.split('.')

suffix='jpg'

if len(temp)>0:

suffix=temp[len(temp)-1]

#print('suffix= '+suffix)

k+=1

with open(path+author_text+str(k)+'.'+suffix,'bw')as f:

print('下载第'+str(j)+'个人'+'第'+str(k)+'照片')

f.write(_session.get(url,verify=True).content)

except:

print('下载图片出了一点问题')

traceback.print_exc()

源码链接：https://pan.baidu.com/s/1o9VVnqa