小甲鱼爬豆瓣TOP250有个代码看不懂
import requestsimport bs4
import re
def open_url(url):
#使用代理
# proxies = {'https':'223.243.174.152:9999','https':'223.214.205.179:9999'}
headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46'}
res = requests.get(url,headers=headers)
return res
def find_movies(res):
#炖汤
soup = bs4.BeautifulSoup(res.text,'html.parser')
#电影名
movies = []
targets = soup.find_all('div',class_ = 'hd')
for each in targets:
movies.append(each.a.span.text)
#评分
ranks = []
targets = soup.find_all('span',class_='rating_num')
for each in targets:
ranks.append('评分%s'%each.text)
#资料
messages = []
targets = soup.find_all('div',class_='bd')
for each in targets:
try:
messages.append(each.p.text.split('\n').strip() + each.p.text.split('\n').strip())
except:
continue
result = []
length = len(movies)
for i in range(length):
result.append(movies + ranks + messages +'\n')
return result
#找出一共有多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text,'html.parser')
depth = soup.find('span',class_= 'next').previous_sibling.previous_sibling.text #这一行什么意思呀?
return int(depth)
def main():
host = 'https://movie.douban.com/top250'
res = open_url(host)
depth = find_depth(res)
result = []
for i in range(depth):
url = host + '/?start='+str(25*i)
res =open_url(url)
result.extend(find_movies(res))
with open('豆瓣TOP250.txt','w',encoding='utf-8') as f:
for each in result:
f.write(each)
if __name__ == '__main__':
main()
我知道previous_sibling是找之前的同级标签,可是我查看了html代码还是只有个大体的猜测,需要大佬们的指导下. https://blog.csdn.net/Winterto1990/article/details/47794941 isdkz 发表于 2022-3-24 23:05
https://blog.csdn.net/Winterto1990/article/details/47794941
可是我看使用两次previous_sibling找到的不应该是9号标签吗? 就是span节点的上一个兄弟节点的上一个兄弟节点，这么说你看你有点乱，我举一个例子吧
In : text = "<div><a>text0</a><b>text1</b><c>text2</c></div>"
In : soup = bs4.BeautifulSoup(text, "html.parser")
In : soup.find("c").previous_sibling.previous_sibling.text
Out: 'text0'
c的上上个兄弟节点就是a，所以拿到的文本是text0 啥子东东啊？？
页:
[1]