我同样的代码为什么在pycharm上打印不出来
import requestsimport bs4
res = requests.get('https://movie.douban.com/top250')
soup = bs4.BeautifulSoup(res.text,'html.parser')
targets = soup.find_all('div',class_ = 'hd')
for each in targets:
print(each.span.text)
在pycharm上打印不出来，有无大佬给解决一下 最后一行的print函数少打了一个a，应该是print(each.a.span.text)，但是就算这样我尝试在pycharm上打印也还是打印不出来啊 本帖最后由 suchocolate 于 2021-11-13 09:57 编辑
import requests
import bs4
headers = {'user-agent': 'Mozilla'}# 替换默认的user-agent, 否则会触发418豆瓣请你喝茶。
res = requests.get('https://movie.douban.com/top250', headers=headers)
soup = bs4.BeautifulSoup(res.text, 'html.parser')
targets = soup.find_all('div', class_='hd')
for each in targets:
print(each.span.text)
suchocolate 发表于 2021-11-13 09:55
大佬哪个print(each.a.span.text)是什么意思，为什么会这样写 哈哈哈ha1 发表于 2021-11-15 14:32
大佬哪个print(each.a.span.text)是什么意思，为什么会这样写
each在循环里就是div，each.a.span.text就是打印 div下的a下的span下的文本内容，一点点就时一个层级。
按我的代码执行应该有东西输出吧？ suchocolate 发表于 2021-11-15 15:19
each在循环里就是div，each.a.span.text就是打印 div下的a下的span下的文本内容，一点点就时一个层级。
...
输出了大佬，可以帮我看一下这个代码么，我爬取豆瓣250电影排行榜，为什么资料和评分那一部分是空的，爬取不到资料和评分，有什么改进的方法么
#完整版代码
import requests
import bs4
import re
def open_url(url):
#使用代理
#proxies = (“http”:"127.0.0.1:1080","https":127.0.0.1:1080)
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
#res = requests.get(url,headers=headers,proxies=proxies)
res = requests.get(url,headers=headers)
return res
def find_movies(res):
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.txt)
#资料
messages = []
targets = soup.find_all('div',class_='bd')
for i 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
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电影.txt','w',encoding='utf-8') as f:
for each in result:
f.write(each)
if __name__ == '__main__':
main() 哈哈哈ha1 发表于 2021-11-15 16:34
输出了大佬，可以帮我看一下这个代码么，我爬取豆瓣250电影排行榜，为什么资料和评分那一部分是空的，爬 ...
import requests
import bs4
import re
def open_url(url):
# 使用代理
# proxies = (“http”:"127.0.0.1:1080","https":127.0.0.1:1080)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
# res = requests.get(url,headers=headers,proxies=proxies)
res = requests.get(url, headers=headers)
return res
def find_movies(res):
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)# 之前写成了each.txt
# 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')# index漏了
return result
# 找出有多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
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电影.txt', 'w', encoding='utf-8') as f:
for each in result:
f.write(each)
if __name__ == '__main__':
main()
import requests
from bs4 import BeautifulSoup
def main():
headers = {'user-agent': 'Mozilla'}
m_name = []
m_score = []
m_info = []
for i in range(10):
url = f'https://movie.douban.com/top250?start={i * 25}'
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, 'html.parser')
m_name.extend(.strip() for item in soup.find_all('div', class_='hd')])
m_score.extend()
info = [item.text.strip().replace('\n', '').replace('\xa0', '')
for item in soup.find_all('div', class_='bd')]
if len(info) > 25:
info = info
m_info.extend(info)
with open('result.txt', 'w', encoding='utf-8') as f:
for i in range(len(m_name)):
f.write(f'{m_name}{m_score}{m_info}\n')
if __name__ == '__main__':
main()
页:
[1]