爬虫数据提取失败
import requests
from bs4 import BeautifulSoup
import time # 导入相应的库文件
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
' AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
} # 加入请求头
def get_info(url):
'''
:param url: 参数：要请求的链接
:return: 空
'''
wb_data = requests.get(url, headers=headers) # 发送网页请求
soup = BeautifulSoup(wb_data.text, 'lxml') # 对网页内容进行解析 wb_data.text表示网页源代码
ranks = soup.select('span.pc_temp_num')
titles = soup.select('div.pc_temp_songlist > u1 > li >a')
times = soup.select('span.pc_temp_tips_r > span')
for rank, title, time in zip(ranks, titles, times):
data = {
'rank': rank.get_text().strip(),
'singer': title.get_text().split('-')[0],
'song': title.get_text().split('-')[1],
'time': time.get_text().strip()
}
print(data)
if __name__ == '__main__':
urls = ['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1,24)] #酷狗音乐
for url in urls:
get_info(url)
time.sleep(1)
运行结果如下
是否是头部访问的地方有问题呢
import requests
from bs4 import BeautifulSoup
import time # 导入相应的库文件
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
' AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
} # 加入请求头
def get_info(url):
'''
:param url: 参数：要请求的链接
:return: 空
'''
wb_data = requests.get(url, headers=headers) # 发送网页请求
soup = BeautifulSoup(wb_data.text, 'lxml') # 对网页内容进行解析 wb_data.text表示网页源代码
ranks = soup.select('span.pc_temp_num')
# titles = soup.select('div.pc_temp_songlist > u1 > li >a')
times = soup.select('span.pc_temp_tips_r > span')
for rank, time in zip(ranks, times):
data = {
'rank': rank.get_text().strip(),
# 'singer': title.get_text().split('-')[0],
# 'song': title.get_text().split('-')[1],
'time': time.get_text().strip()
}
print(data)
if __name__ == '__main__':
urls = ['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1,24)] #酷狗音乐
for url in urls:
get_info(url)
time.sleep(1)