75 lines
2.8 KiB
Python
75 lines
2.8 KiB
Python
import csv
|
|
import requests
|
|
from lxml import etree
|
|
|
|
|
|
class YXZS:
|
|
def __init__(self) -> None:
|
|
self.url = "https://yz.chsi.com.cn/sch/?start={}"
|
|
self.file = open("./data.csv", "+a", encoding="utf-8", newline="")
|
|
self.file.write("学校名称,学校性质,招生简章的链接,调剂办法的链接\n")
|
|
|
|
def get_html(self, page=1):
|
|
resp = requests.get(
|
|
self.url.format((page - 1) * 20),
|
|
headers={
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36 Edg/140.0.0.0",
|
|
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
|
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
|
|
},
|
|
)
|
|
if resp.status_code == 200:
|
|
return resp.text
|
|
return ""
|
|
|
|
def parse_html(self, html_text: str):
|
|
html = etree.HTML(html_text)
|
|
schs = html.xpath('//div[@class="sch-item"]')
|
|
for sch in schs:
|
|
item = {
|
|
"name": (
|
|
sch.xpath(
|
|
'.//a[@class="name js-yxk-yxmc text-decoration-none"]/text()'
|
|
)[0].strip()
|
|
if sch.xpath(
|
|
'.//a[@class="name js-yxk-yxmc text-decoration-none"]/text()'
|
|
)
|
|
else "unkonwn"
|
|
),
|
|
"tag": (
|
|
sch.xpath('.//span[@class="sch-tag"]/text()')[0].strip()
|
|
if sch.xpath('.//span[@class="sch-tag"]/text()')
|
|
else "unkonwn"
|
|
),
|
|
"href1": (
|
|
"https://yz.chsi.com.cn"
|
|
+ sch.xpath('.//div[@class="sch-link"]/a[2]/@href')[0]
|
|
if sch.xpath('.//div[@class="sch-link"]/a[2]/@href')
|
|
else "unkonwn"
|
|
),
|
|
"href2": (
|
|
"https://yz.chsi.com.cn"
|
|
+ sch.xpath('.//div[@class="sch-link"]/a[4]/@href')[0]
|
|
if sch.xpath('.//div[@class="sch-link"]/a[4]/@href')
|
|
else "unkonwn"
|
|
),
|
|
}
|
|
self.save_data(item)
|
|
|
|
def save_data(self, item):
|
|
writer = csv.DictWriter(self.file, fieldnames=item.keys())
|
|
writer.writerow(item)
|
|
|
|
def run(self):
|
|
for i in range(0, 47):
|
|
print("正在获取第{}页".format(i + 1))
|
|
html_text = self.get_html(page=i)
|
|
if html_text == "":
|
|
print("第{}页获取的内容为空")
|
|
continue
|
|
self.parse_html(html_text)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
YXZS().run()
|