You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
83 lines
2.3 KiB
83 lines
2.3 KiB
6 months ago
|
from lxml import etree
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
import re
|
||
|
|
import requests
|
||
|
|
|
||
|
|
url = "https://www.ncrczpw.com/index.php?m=jobfair&c=index&a=index"
|
||
|
|
headers = {"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
|
||
|
|
'Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0'}
|
||
|
|
res = requests.get(url, headers=headers)
|
||
|
|
html = res.text
|
||
|
|
# print(html)
|
||
|
|
url = []
|
||
|
|
soup = BeautifulSoup(html, "lxml")
|
||
|
|
y = soup.select("div.tit")
|
||
|
|
for i in y:
|
||
|
|
z = i.find_all(name="a")
|
||
|
|
for a in z:
|
||
|
|
k = a.get("href")
|
||
|
|
if k is not None:
|
||
|
|
# print(k)
|
||
|
|
urls.append(k)
|
||
|
|
# print(urls[1:])
|
||
|
|
|
||
|
|
ll = []
|
||
|
|
for g in url[1:]:
|
||
|
|
# print(g)
|
||
|
|
list = []
|
||
|
|
res1 = requests.get(g, headers=headers)
|
||
|
|
htmls = res1.text
|
||
|
|
# print(htmls)
|
||
|
|
soup1 = BeautifulSoup(htmls, "lxml")
|
||
|
|
y1 = soup1.find_all("div", class_='txt')
|
||
|
|
# print(len(y1))
|
||
|
|
if len(y1) == 10:
|
||
|
|
list.append(y1[0].text.strip())
|
||
|
|
list.append(y1[1].text.strip())
|
||
|
|
list.append(y1[4].text.strip())
|
||
|
|
list.append(86700710)
|
||
|
|
list.append(y1[5].text.strip())
|
||
|
|
|
||
|
|
# print(list1)
|
||
|
|
y2 = soup1.find_all("strong")
|
||
|
|
list2 = []
|
||
|
|
for i in y2:
|
||
|
|
list2.append(i.text.strip())
|
||
|
|
list.append('、'.join(list2))
|
||
|
|
ll.append(list)
|
||
|
|
if len(y1) == 9:
|
||
|
|
list.append(y1[0].text.strip())
|
||
|
|
list.append(y1[1].text.strip())
|
||
|
|
list.append(y1[3].text.strip())
|
||
|
|
list.append(86700710)
|
||
|
|
list.append(y1[4].text.strip())
|
||
|
|
|
||
|
|
# print(list1)
|
||
|
|
y2 = soup1.find_all("strong")
|
||
|
|
list2 = []
|
||
|
|
for i in y2:
|
||
|
|
list2.append(i.text.strip())
|
||
|
|
list.append('、'.join(list2))
|
||
|
|
ll.append(list)
|
||
|
|
|
||
|
|
if len(y1) == 1:
|
||
|
|
span = soup1.find_all('span')
|
||
|
|
h1 = soup1.find_all('h1')
|
||
|
|
|
||
|
|
if not h1:
|
||
|
|
list.append(h1)
|
||
|
|
else:
|
||
|
|
list.append(h1[0])
|
||
|
|
list.append(span[5].text.strip())
|
||
|
|
list.append(span[3].text.strip())
|
||
|
|
list.append(86700710)
|
||
|
|
list.append('')
|
||
|
|
|
||
|
|
# print(list1)
|
||
|
|
y2 = soup1.select('ul>li>a.companyName')
|
||
|
|
list2 = []
|
||
|
|
for i in y2:
|
||
|
|
list2.append(i.text.strip())
|
||
|
|
list.append('、'.join(list2))
|
||
|
|
ll.append(list)
|
||
|
|
print(ll)
|