菜鸟学习之路，学习python断断续续不知道第多少天的我

聪明小米

第一个实习僧职位爬虫

• import requests
  from bs4 import BeautifulSoup
  def get_soups(url):
  html = requests.get(url)
  soup = BeautifulSoup(html.text, 'lxml')
  return soup
  def job_names(url): # 获取工作名称
  job_name = get_soups(url).select('.new_job_name')[0].get('title')
  return job_name
  def company_names(url): # 获取公司名称
  company_name = get_soups(url).select('.com-name')[0].text
  company_name = company_name.split('\n')[1]
  return company_name
  def company_profiles(url): # 获取公司简介
  company_profile = get_soups(url).select('.com-desc')[0].text
  return company_profile
  def job_salaries(url): # 获取薪资
  job_salary = get_soups(url).select(
  '.job-box .job_msg .job_money')[0].text.encode('utf-8')
  job_salary = job_salary.replace(b'\xef\x85\x9b', b'0')
  job_salary = job_salary.replace(b'\xef\x97\xa7', b'1')
  job_salary = job_salary.replace(b'\xee\x9c\x83', b'2')
  job_salary = job_salary.replace(b'\xee\xbd\xa0', b'3')
  job_salary = job_salary.replace(b'\xee\xbb\xab', b'4')
  job_salary = job_salary.replace(b'\xee\x9e\x82', b'5')
  job_salary = job_salary.replace(b'\xee\xbb\x95', b'8')
  job_salary = job_salary.decode()
  return job_salary
  for page in range(0, 20):
  offers = get_soups(f'https://www.shixiseng.com/interns?page={page}&type=intern&keyword=Python').select(
  '.intern-wrap.intern-item .f-l.intern-detail__job a')
  for offer in offers:
  url = offer.get('href')
  job_name = job_names(url)
  compamy_name = company_names(url)
  company_profile = company_profiles(url)
  job_salary = job_salaries(url)
  print(
  f'工作名称：{job_name}\n公司名称:{compamy_name}\n公司简介：{company_profile}\n工作薪资：{job_salary}'+'\n')
  

复制代码
第二个糗事百科段子爬虫

• import requests
  from bs4 import BeautifulSoup
  def get_soups(url):
  req = requests.get(url)
  # print(req.status_code)
  html = req.text
  soup = BeautifulSoup(html, 'lxml')
  return soup
  def get_author(url):
  result = get_soups(url)
  author = result.select('.side-user-top a')
  author = author[0].get('title')
  return author
  def get_content(url):
  result = get_soups(url)
  content = result.select('.content')[0].text
  return content
  for page in range(0, 20):
  link = f'https://www.qiushibaike.com/text/page/{page}/'
  result = get_soups(link)
  jokes = result.select('.contentHerf')
  for joke in jokes:
  joke_url = joke.get('href')
  url = 'https://www.qiushibaike.com'+joke_url
  author = get_author(url)
  content = get_content(url)
  print(f'作者：{author}\n内容：\n{content}\n\n\n')
  

复制代码
弄了一个下午 淦淦淦淦淦淦淦淦淦淦淦

超级小爱

有点东西，蹲个实际体验