To see how .net employment market, with a python crawling Xiamen Talent Network Information .net posts, did not talk much on the code, did not learn how long python, what if something wrong, please correct me
import requests
from bs4 import BeautifulSoup
page = 1;
def loop(page):
url = "https://www.xmrc.com.cn/net/info/resultg.aspx?a=a&g=g&jobtype=&releaseTime=365&searchtype=1&keyword=.net&sortby=updatetime&ascdesc=Desc&PageIndex=%s"%page;
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
allJob = soup.select(".a4.js_companyName");
companys = []
Others = []
for x in range(0,len(allJob)):
job = allJob[x].get_text().strip()
print(job);
other = allJob[x].parent.findPrevious("td").get_text().strip() + ","+ allJob[x].parent.findNext("td").get_text().strip() + "," + allJob[x].parent.findNext("td").findNext("td").get_text().strip();
print(other);
companys.append(job)
Others.append(other)
return companys, Others;
for x in range(0,20):
companys,Others = loop(x)
with open('company.txt', 'a', encoding='utf-8') as f:
for x in range(0,len(companys)):
f.write(str(companys[x] + "," + Others[x]) + '\n')