网站需要在哪些方面备案/广州百度推广外包
我开通了公众号【智能制造专栏】，以后技术类文章会发在专栏。
用Python写爬虫是很方便的,最近看了xlzd.me的文章，他的文章写的很到位，提供了很好的思路。因为他的文章部分代码省略了。下面是基于他的文章的三个代码片段:
基于Python3,Python2的话需要修改下input输入函数和print的用法。本文github代码地址
爬取豆瓣电影top250
爬取拉勾网职位信息
模拟登陆知乎
为什么没人给我点赞。？！
有些代码做了更改。其中把获取的数据存储到excel中。关于存取数据到excel可以看我的另一篇文章：。
用到的库
requests
Beautiful Soup
openpyxl
1. 爬取豆瓣电影top250，存到excel表格中
#!/usr/bin/env python
# encoding=utf-8
import requests,re
import codecs
from bs4 import BeautifulSoup
from openpyxl import Workbook
wb = Workbook()
dest_filename = '电影.xlsx'
ws1 = wb.active
ws1.title = "电影top250"
DOWNLOAD_URL = 'http://movie.douban.com/top250/'
def download_page(url):
"""获取url地址页面内容"""
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'
}
data = requests.get(url, headers=headers).content
return data
def get_li(doc):
soup = BeautifulSoup(doc, 'html.parser')
ol = soup.find('ol', class_='grid_view')
name = [] #名字
star_con = [] #评价人数
score = [] #评分
info_list = [] #短评
for i in ol.find_all('li'):
detail = i.find('div', attrs={'class': 'hd'})
movie_name = detail.find('span', attrs={'class': 'title'}).get_text() #电影名字
level_star = i.find('span',attrs={'class':'rating_num'}).get_text() #评分
star = i.find('div',attrs={'class':'star'})
star_num = star.find(text=re.compile('评价')) #评价
info = i.find('span',attrs={'class':'inq'}) #短评
if info: #判断是否有短评
info_list.append(info.get_text())
else:
info_list.append('无')
score.append(level_star)
name.append(movie_name)
star_con.append(star_num)
page = soup.find('span', attrs={'class': 'next'}).find('a') #获取下一页
if page:
return name,star_con,score,info_list,DOWNLOAD_URL + page['href']
return name,star_con,score,info_list,None
def main():
url = DOWNLOAD_URL
name = []
star_con=[]
score = []
info = []
while url:
doc = download_page(url)
movie,star,level_num,info_list,url = get_li(doc)
name = name + movie
star_con = star_con + star
score = score+level_num
info = info+ info_list
for (i,m,o,p) in zip(name,star_con,score,info):
col_A = 'A%s'%(name.index(i)+1)
col_B = 'B%s'%(name.index(i)+1)
col_C = 'C%s'%(name.index(i)+1)
col_D = 'D%s'%(name.index(i)+1)
ws1[col_A]=i
ws1[col_B] = m
ws1[col_C] = o
ws1[col_D] = p
wb.save(filename=dest_filename)
if __name__ == '__main__':
main()
结果如下：
2. 爬取拉勾网Python职位信息
职位信息存储在json中，获取到json对象，再从中遍历出公司名、地址、待遇等信息。
import requests
from openpyxl import Workbook
def get_json(url, page, lang_name):
data = {'first': 'true', 'pn': page, 'kd': lang_name}
json = requests.post(url, data).json()
list_con = json['content']['positionResult']['result']
info_list = []
for i in list_con:
info = []
info.append(i['companyShortName'])
info.append(i['companyName'])
info.append(i['salary'])
info.append(i['city'])
info.append(i['education'])
info_list.append(info)
return info_list
def main():
lang_name = input('职位名：')
page = 1
url = 'http://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
info_result = []
while page < 31:
info = get_json(url, page, lang_name)
info_result = info_result + info
page += 1
wb = Workbook()
ws1 = wb.active
ws1.title = lang_name
for row in info_result:
ws1.append(row)
wb.save('职位信息.xlsx')
if __name__ == '__main__':
main()
运行结果：
3. 模拟登录知乎
通过开发者工具，获取post的数据。
import requests,time
from bs4 import BeautifulSoup
def get_captcha(data):
with open('captcha.gif','wb') as fp:
fp.write(data)
return input('输入验证码：')
def login(username,password,oncaptcha):
sessiona = requests.Session()
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'}
_xsrf = BeautifulSoup(sessiona.get('https://www.zhihu.com/#signin',headers=headers).content,'html.parser').find('input',attrs={'name':'_xsrf'}).get('value')
captcha_content = sessiona.get('https://www.zhihu.com/captcha.gif?r=%d&type=login'%(time.time()*1000),headers=headers).content
data = {
"_xsrf":_xsrf,
"email":username,
"password":password,
"remember_me":True,
"captcha":oncaptcha(captcha_content)
}
resp = sessiona.post('https://www.zhihu.com/login/email',data,headers=headers).content
print(resp)
return resp
if __name__ == "__main__":
login('your_email','your_password',get_captcha)
运行后会在运行目录下得到验证码图片：
输入验证码后得到如下响应结果表明登录成功。
