【python爬虫 系列】14.实战三 爬取实习僧

主要是字体反爬虫，逐一破解即可

#爬取实习僧 最新版本
import requests
from bs4 import BeautifulSoup


kv={"user-agent":'Mozilla/5.0'}
def detail_page(url):
	req = requests.get(url,headers=kv)
	html = req.text
	soup = BeautifulSoup(html,'lxml')

	job_name = soup.select('.new_job_name span')[0].string
	job_company = soup.select('.com-name')[0].string
	job_money = soup.select('.job_msg span')[0].string

	job_money = job_money.encode("utf-8")
	job_money = job_money.replace(b'\xee\x8c\x85',b'0')
	job_money = job_money.replace(b'\xee\xaa\x9f',b'1')
	job_money = job_money.replace(b'\xee\x9f\xa1',b'2')
	job_money = job_money.replace(b'\xef\x8a\x97',b'3')
	job_money = job_money.replace(b'\xee\x82\xab',b'4')
	job_money = job_money.replace(b'\xee\x82\x87',b'5')
	job_money = job_money.replace(b'\xee\xad\xb7',b'6')
	job_money = job_money.replace(b'\xee\xae\x80',b'7')
	job_money = job_money.replace(b'\xee\xb2\xbf',b'8')
	job_money = job_money.replace(b'\xee\xb3\x9e',b'9')
	job_money = job_money.decode()

	job_academic = soup.select('.job_academic')[0].string
	job_time = soup.select('.job_time')[0].string

	job_time = job_time.encode("utf-8")
	job_time = job_time.replace(b'\xee\x8c\x85',b'0')
	job_time = job_time.replace(b'\xee\xaa\x9f',b'1')
	job_time = job_time.replace(b'\xee\x9f\xa1',b'2')
	job_time = job_time.replace(b'\xef\x8a\x97',b'3')
	job_time = job_time.replace(b'\xee\x82\xab',b'4')
	job_time = job_time.replace(b'\xee\x82\x87',b'5')
	job_time = job_time.replace(b'\xee\xad\xb7',b'6')
	job_time = job_time.replace(b'\xee\xae\x80',b'7')
	job_time = job_time.replace(b'\xee\xb2\xbf',b'8')
	job_time = job_time.replace(b'\xee\xb3\x9e',b'9')
	job_time = job_time.decode()

	job_week = soup.select('.job_week')[0].string

	job_week = job_week.encode("utf-8")
	job_week = job_week.replace(b'\xee\x8c\x85',b'0')
	job_week = job_week.replace(b'\xee\xaa\x9f',b'1')
	job_week = job_week.replace(b'\xee\x9f\xa1',b'2')
	job_week = job_week.replace(b'\xef\x8a\x97',b'3')
	job_week = job_week.replace(b'\xee\x82\xab',b'4')
	job_week = job_week.replace(b'\xee\x82\x87',b'5')
	job_week = job_week.replace(b'\xee\xad\xb7',b'6')
	job_week = job_week.replace(b'\xee\xae\x80',b'7')
	job_week = job_week.replace(b'\xee\xb2\xbf',b'8')
	job_week = job_week.replace(b'\xee\xb3\x9e',b'9')
	job_week = job_week.decode()

	job_position = soup.select('.job_position')[0].string

	contents = {"工作名字：{}，公司：{}，工薪：{}，要求学历：{}，工作时间:{},实习周期：{}，地点：{}".format(job_name,job_company,job_money,job_academic,job_time,job_week,job_position)} 
	print(contents)


for page in range(1,2):
	url = 'https://www.shixiseng.com/bj/it/{}'.format(page)
	req = requests.get(url,headers=kv)
	html = req.text
	soup = BeautifulSoup(html,'lxml')
	articles = soup.select('p a')
	##print(articles)
	for item in articles:

		detail_url = item.get("href")
		if len(detail_url) >48:
			new = detail_url
			detail_page(new)
	
#detail_page("https://www.shixiseng.com/intern/inn_ss9mdklhvlsx")  破解编码
'''b'\xee\xaa\x9f\xee\x8c\x85\xee\x8c\x85-\xee\xaa\x9f\xee\x82\x87\xee\x8c\x85/\xe5\xa4\xa9'
100-150/天     3个  
\xee\xaa\x9f   1
\xee\x8c\x85   0
\xee\x82\x87   5
b'\xee\xaa\x9f\xee\x8c\x85\xee\x8c\x85-\xee\xaa\x9f\xee\x9f\xa1\xee\x8c\x85/\xe5\xa4\xa9'
100-120
\xee\x9f\xa1   2
b'\xee\xaa\x9f\xee\x82\x87\xee\x8c\x85-\xef\x8a\x97\xee\x8c\x85\xee\x8c\x85/\xe5\xa4\xa9'
150-300
\xef\x8a\x97   3
b'\xee\xaa\x9f\xee\x9f\xa1\xee\x8c\x85-\xee\xaa\x9f\xee\xb2\xbf\xee\x8c\x85/\xe5\xa4\xa9'
120-180
\xee\xb2\xbf   8
b'\xee\xaa\x9f\xee\x82\xab\xee\x8c\x85-\xee\x9f\xa1\xee\x8c\x85\xee\x8c\x85/\xe5\xa4\xa9'
140-200
\xee\x82\xab   4
b'\xee\x82\xab\xee\x8c\x85-\xee\xad\xb7\xee\x8c\x85/\xe5\xa4\xa9'
\xee\xad\xb7   6
b'\xee\xaa\x9f\xee\x8c\x85\xee\x8c\x85-\xee\xaa\x9f\xee\xb3\x9e\xee\xae\x80/\xe5\xa4\xa9'
100-197
\xee\xb3\x9e  9
\xee\xae\x80  7
'''