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.
80 lines
3.9 KiB
80 lines
3.9 KiB
2 months ago
|
import requests
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
import pandas as pd
|
||
|
|
|
||
|
|
# 伪造请求头
|
||
|
|
headers = {
|
||
|
|
'cookie': 'ASP.NET_SessionSvc=MTAuMTEzLjkyLjkzfDkwOTB8b3V5YW5nfGRlZmF1bHR8MTYzODQzNDE5NTI2NQ; _bfa=1.1727420783628.2v4j7k.1.1727420783628.1727420783628.1.1.154019; _ubtstatus=%7B%22vid%22%3A%221727420783628.2v4j7k%22%2C%22sid%22%3A1%2C%22pvid%22%3A1%2C%22pid%22%3A154019%7D; Hm_lvt_e4211314613fcf074540918eb10eeecb=1727420784; Hm_lpvt_e4211314613fcf074540918eb10eeecb=1727420784; HMACCOUNT=34C5D5D87EFFB691; GUID=09031042416180792327; MKT_CKID=1727420785262.vgfup.ox1u; _jzqco=%7C%7C%7C%7C1727420785652%7C1.608322706.1727420785265.1727420785265.1727420785265.1727420785265.1727420785265.0.0.0.1.1; _RF1=182.88.188.57; _RSG=SnajKuQaCp5rinW_EZPRm8; _RDG=28338c247be07326791c678684a664d512; _RGUID=5ccc91ae-14b6-4c5c-8c1b-6633bf831b35; _bfaStatusPVSend=1; _bfaStatus=success; _bfi=p1%3D154019%26p2%3D0%26v1%3D1%26v2%3D0',
|
||
|
|
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36'
|
||
|
|
}
|
||
|
|
|
||
|
|
dic = []
|
||
|
|
|
||
|
|
|
||
|
|
def work(url, headers, cuisine):
|
||
|
|
# 发送请求
|
||
|
|
response = requests.get(url, headers=headers)
|
||
|
|
# 使用BeautifulSoup解析HTML
|
||
|
|
soup = BeautifulSoup(response.text, 'lxml')
|
||
|
|
|
||
|
|
# 获取所有标签
|
||
|
|
li_elements = soup.find('div', class_='list_wide_mod2').find_all('div', class_='list_mod2')
|
||
|
|
for div in li_elements:
|
||
|
|
# 人均消费
|
||
|
|
renjun = div.find_next('div', class_='rdetailbox').find('dl').find_all('dd')[1].find_next('span').text
|
||
|
|
renjun = renjun.replace('￥', '')
|
||
|
|
# 餐厅评分
|
||
|
|
pingfen = div.find_next('div', class_='rdetailbox').find('ul').find_all('li')[0].find_next('a').text
|
||
|
|
pingfen = pingfen.replace('\xa0分', '')
|
||
|
|
# 餐厅链接
|
||
|
|
lianjie = div.find_next('div', class_='rdetailbox').find('dl').find('dt').find('a').get('href')
|
||
|
|
xiechen_url = 'https://you.ctrip.com' + lianjie
|
||
|
|
# 发送请求
|
||
|
|
xiechen_response = requests.get(xiechen_url, headers=headers)
|
||
|
|
# 使用BeautifulSoup解析HTML
|
||
|
|
xiechen_soup = BeautifulSoup(xiechen_response.text, 'lxml')
|
||
|
|
evaluation_number = xiechen_soup.find('ul', class_='tablist').find_all('li')
|
||
|
|
# 餐厅名称
|
||
|
|
name = xiechen_soup.find('div', class_='f_left').find('h1').text
|
||
|
|
# 评论数量
|
||
|
|
total_comments = xiechen_soup.find('dfn', id='hrefyyDp').find('span', class_='f_orange').text
|
||
|
|
# 每种评价数量
|
||
|
|
detailed_scoring = {}
|
||
|
|
for num in evaluation_number:
|
||
|
|
index1 = num.find_next('a').text.find('(')
|
||
|
|
index2 = num.find_next('a').text.find(')')
|
||
|
|
detailed_scoring = {**detailed_scoring,
|
||
|
|
num.find_next('a').text[0:index1]: num.find_next('a').text[index1 + 1:index2]}
|
||
|
|
data = {
|
||
|
|
'餐厅名称': name,
|
||
|
|
'人均消费': renjun,
|
||
|
|
'评分': pingfen,
|
||
|
|
'餐厅链接': xiechen_url,
|
||
|
|
'评论总数': total_comments,
|
||
|
|
**detailed_scoring,
|
||
|
|
'菜系': cuisine
|
||
|
|
}
|
||
|
|
dic.append(data)
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
# 菜系字典
|
||
|
|
# "火锅","广西菜","西餐","烧烤","川菜","粤菜","湘菜","鲁菜","闽菜","徽菜"
|
||
|
|
cuisine_dic = {'火锅': 4903, '广西菜': 4918,'西餐':4900,'烧烤':4931,'川菜':4896,'粤菜':4898,'湘菜':4915,'鲁菜':4920,'闽菜':4916,'徽菜':4911}
|
||
|
|
# 一页15条数据
|
||
|
|
for key in cuisine_dic:
|
||
|
|
for i in range(1, 2):
|
||
|
|
# 请求地址
|
||
|
|
url = f'https://you.ctrip.com/restaurantlist/China110000/list-c{cuisine_dic[key]}-p{i}.html'
|
||
|
|
# 调用函数
|
||
|
|
work(url=url, headers=headers, cuisine=key)
|
||
|
|
# 打印结果
|
||
|
|
print(dic)
|
||
|
|
# 将结果保存到excel
|
||
|
|
df = pd.DataFrame(dic)
|
||
|
|
df.to_excel('携程餐厅数据.xlsx', index=False)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
main()
|