python爬虫的时候想提取URL但是提取不全

Question

python爬虫的时候想提取URL但是提取不全

import bs4 as bs
import urllib.request
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from functools import wraps
source = urllib.request.urlopen("https://www.formula1.com/en/results.html/2021/race.html").read()
soup = bs.BeautifulSoup(source,'lxml')
all_urls = soup.find_all('a')
race_urls = []
for url in all_urls:
    if ('2021' in str(url.get('href'))) and ('fastest-laps' in str(url.get('href')))and (url.get('href') not in race_urls) :
            race_urls.append(url.get('href'))
race_urls

最后出来的只有一个['/en/results.html/2021/fastest-laps.html']，应该有22个才对，请各位解答。本人初学勿喷。

Answer 1

是被你的过滤条件过滤了吧，检查一下过滤条件：

import bs4 as bs
import urllib.request
source = urllib.request.urlopen("https://www.formula1.com/en/results.html/2021/races/1068/azerbaijan/race-result.html").read()
soup = bs.BeautifulSoup(source,'lxml')
all_urls = soup.find_all('a')
race_urls = []
for url in all_urls:
    if ('2021' in str(url.get('href'))) and (url.get('href') not in race_urls) :
            race_urls.append(url.get('href'))


print(race_urls)
print(len(race_urls))