作为一个Python小白,在经过一个大牛的安利下,迅速将魔爪伸向了Python。作为一个小白,今天分享下已经被大牛们玩坏的知乎爬虫,各位看官你看好了。
1. 我为什么要爬取回答
其实我只是好奇,加上为了快速掌握基本的语法,就研究了一下。
2. 如何实现
懒得说了,你自己看代码吧:
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Filename : ZhiHuSpider.py
import time
import re
import requests
import http.cookiejar
from PIL import Image
import json
from bs4 import BeautifulSoup
class ZhiHuSpider(object):
def __init__(self):
self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36',
"Host": "www.zhihu.com",
"Referer": "https://www.zhihu.com/",
}
# 建立一个会话,可以把同一用户的不同请求联系起来;直到会话结束都会自动处理cookies
self.session = requests.Session()
self.session.keep_alive = False
# 建立LWPCookieJar实例,可以存Set-Cookie3类型的文件。
# 而MozillaCookieJar类是存为'/.txt'格式的文件
self.session.cookies = http.cookiejar.LWPCookieJar("cookie")
# 若本地有cookie则不用再post数据了
try:
self.session.cookies.load(ignore_discard=True)
print('Cookie加载成功!')
except IOError:
print('Cookie未加载!')
def get_xsrf(self):
"""
获取参数_xsrf
"""
response = self.session.get('https://www.zhihu.com', headers=self.headers)
html = response.text
get_xsrf_pattern = re.compile(r'<input type="hidden" name="_xsrf" value="(.*?)"')
_xsrf = re.findall(get_xsrf_pattern, html)[0]
return _xsrf
def get_captcha(self):
"""
获取验证码本地显示
返回你输入的验证码
"""
t = str(int(time.time() * 1000))
captcha_url = 'http://www.zhihu.com/captcha.gif?r=' + t + "&type=login"
response = self.session.get(captcha_url, headers=self.headers)
with open('cptcha.gif', 'wb') as f:
f.write(response.content)
# Pillow显示验证码
im = Image.open('cptcha.gif')
im.show()
captcha = input('本次登录需要输入验证码: ')
return captcha
def login(self, username, password):
"""
输入自己的账号密码,模拟登录知乎
"""
# 检测到11位数字则是手机登录
if re.match(r'\d{11}$', username):
url = 'http://www.zhihu.com/login/phone_num'
data = {'_xsrf': self.get_xsrf(),
'password': password,
'remember_me': 'true',
'phone_num': username
}
else:
url = 'https://www.zhihu.com/login/email'
data = {'_xsrf': self.get_xsrf(),
'password': password,
'remember_me': 'true',
'email': username
}
# 若不用验证码,直接登录
result = self.session.post(url, data=data, headers=self.headers)
# 打印返回的响应,r = 1代表响应失败,msg里是失败的原因
# loads可以反序列化内置数据类型,而load可以从文件读取
if (json.loads(result.text))["r"] == 1:
# 要用验证码,post后登录
data['captcha'] = self.get_captcha()
result = self.session.post(url, data=data, headers=self.headers)
print((json.loads(result.text))['msg'])
# 保存cookie到本地
self.session.cookies.save(ignore_discard=True, ignore_expires=True)
def isLogin(self):
# 通过查看用户个人信息来判断是否已经登录
url = "https://www.zhihu.com/settings/profile"
# 禁止重定向,否则登录失败重定向到首页也是响应200
login_code = self.session.get(url, headers=self.headers, allow_redirects=False,verify=False).status_code
if login_code == 200:
return True
else:
return False
def getUserInfo(self, userId):
url = 'https://www.zhihu.com/people/' + userId + '/activities'
response = self.session.get(url, headers=self.headers)
soup = BeautifulSoup(response.content, 'lxml')
name = soup.find_all('span', {'class': 'ProfileHeader-name'})[0].string
print(name)
def getQsAnswer(self, questionId):
# 每次我们取10条回答
limit = 10
# 获取答案时的偏移量
offset = 0
# 开始时假设当前有这么多的回答,得到请求后我再解析
total = 2 * limit;
# 我们当前已记录的回答数量
record_num = 0
# 定义问题的标题,为了避免获取失败,我们在此先赋值
title = questionId
# 存储所有的答案信息
answer_info = []
print('Fetch info start...')
while record_num < total:
# 开始获取数据
# 我们获取数据的URL格式是什么样呢?
# https://www.zhihu.com/api/v4/questions/39162814/answers?
# sort_by=default&include=data[*].is_normal,content&limit=5&offset=0
url = 'https://www.zhihu.com/api/v4/questions/' \
+ questionId + '/answers' \
'?sort_by=default&include=data[*].is_normal,voteup_count,content' \
'&limit=' + str(limit) + '&offset=' + str(offset)
response = self.session.get(url, headers=self.headers)
# 返回的信息为json类型
response = json.loads(response.content)
# 其中的paging实体包含了前一页&下一页的URL,可据此进行循环遍历获取回答的内容
# 我们先来看下总共有多少回答
total = response['paging']['totals']
# 本次请求返回的实体信息数组
datas = response['data']
# 遍历信息并记录
if datas is not None:
if total <= 0:
break
for data in datas:
dr = re.compile(r'<[^>]+>', re.S)
content = dr.sub('', data['content'])
answer = data['author']['name'] + ' ' + str(data['voteup_count']) + ' 人点赞' + '\n'
answer = answer + 'Answer:' + content + '\n'
answer_info.append('\n')
answer_info.append(answer)
answer_info.append('\n')
answer_info.append('------------------------------')
answer_info.append('\n')
# 获取问题的title
title = data['question']['title']
# 请求的向后偏移量
offset += len(datas)
record_num += len(datas)
# 如果获取的数组size小于limit,循环结束
if len(datas) < limit:
break;
print('Fetch info end...')
answer_info.insert(0, title + '\n')
self.write2File(title + '.txt', answer_info)
def write2File(self, filePath, answerInfo):
print('Write info to file:Start...')
# 将文件内容写到文件中
with open(filePath, 'a', encoding='utf-8') as f:
f.writelines('\n\n')
for text in answerInfo:
f.writelines(text)
f.writelines('\n\n')
print('Write info to file:end...')
if __name__ == '__main__':
spider = ZhiHuSpider()
if spider.isLogin():
print('您已经登录')
else:
account = input('输入账号:')
secret = input('输入密码:')
spider.login(account, secret)
# spider.getQsAnswer('39162814')
# spider.getQsAnswer('57702309')
spider.getQsAnswer('49525749')
3. 总结
我注释写的那么详细,如果存在疑问,欢迎留言。
网友评论
https://www.zhihu.com/api/v4/questions/56011472/answers?include=data%5B%2A%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Ccreated_time%2Cupdated_time%2Creview_info%2Crelevant_info%2Cquestion%2Cexcerpt%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%2A%5D.mark_infos%5B%2A%5D.url%3Bdata%5B%2A%5D.author.follower_count%2Cbadge%5B%3F%28type%3Dbest_answerer%29%5D.topics&;limit=5&offset=10&sort_by=default
错误提示:
C:\Program Files\Python36\lib\site-packages\urllib3\connectionpool.py:858: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
InsecureRequestWarning)
C:\Program Files\Python36\lib\site-packages\urllib3\connectionpool.py:858: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
InsecureRequestWarning)
Traceback (most recent call last):
File "zhihu_answer_download.py", line 200, in <module>
spider.login(account, secret)
File "zhihu_answer_download.py", line 75, in login
data = {'_xsrf': self.get_xsrf(),
File "zhihu_answer_download.py", line 41, in get_xsrf
_xsrf = re.findall(get_xsrf_pattern, html)[0]
IndexError: list index out of range
https://www.zhihu.com/api/v4/questions/39162814/answers?sort_by=default&include=data[*].is_normal,content&limit=5&offset=0