Python如何使用BeautifulSoup爬取网页信息

def get_one_page(url):
  response = requests.get(url)
  soup = BeautifulSoup(response.text, "html.parser")
  return soup

def parse_page(soup):
  #待存储的信息列表
  return_list = []
  #起始位置
  grid = soup.find('section', attrs={"class": "widget-job-list"})
  if grid:
    #找到所有的岗位列表
    job_list = soup.find_all('article', attrs={"class": "widget item"})

    #匹配各项内容
    for job in job_list:
      #find()是寻找第一个符合的标签
      company = job.find('a', attrs={"class": "crop"}).get_text().strip()#返回类型为string，用strip（）可以去除空白符，换行符
      title = job.find('code').get_text()
      salary = job.find('span', attrs={"class": "color-3"}).get_text()
      #将信息存到列表中并返回
      return_list.append(company + " " + title + " " + salary)
  return return_list

def write_to_file(content):
  #以追加的方式打开，设置编码格式防止乱码
  with open("shixi.csv", "a", encoding="gb18030")as f:
    f.write("\n".join(content))

def main(page):
  url = 'https://www.ciweishixi.com/search?key=python&page=' + str(page)
  soup = get_one_page(url)
  return_list = parse_page(soup)
  write_to_file(return_list)
if __name__ == "__main__":
  for i in range(4):
    main(i)

import requests
import re
from bs4 import BeautifulSoup

def get_one_page(url):
  response = requests.get(url)
  soup = BeautifulSoup(response.text, "html.parser")
  return soup

def parse_page(soup):
  #待存储的信息列表
  return_list = []
  #起始位置
  grid = soup.find('section', attrs={"class": "widget-job-list"})
  if grid:
    #找到所有的岗位列表
    job_list = soup.find_all('article', attrs={"class": "widget item"})

    #匹配各项内容
    for job in job_list:
      #find()是寻找第一个符合的标签
      company = job.find('a', attrs={"class": "crop"}).get_text().strip()#返回类型为string，用strip（）可以去除空白符，换行符
      title = job.find('code').get_text()
      salary = job.find('span', attrs={"class": "color-3"}).get_text()
      #将信息存到列表中并返回
      return_list.append(company + " " + title + " " + salary)
  return return_list

def write_to_file(content):
  #以追加的方式打开，设置编码格式防止乱码
  with open("shixi.csv", "a", encoding="gb18030")as f:
    f.write("\n".join(content))
def main(page):
  url = 'https://www.ciweishixi.com/search?key=python&page=' + str(page)
  soup = get_one_page(url)
  return_list = parse_page(soup)
  write_to_file(return_list)
if __name__ == "__main__":
  for i in range(4):
    main(i)