问题遇到的现象和发生背景
爬电影信息，真的试了很多方法都没找到问题出来哪里。
现在不知道为什么完全不允许中间的loading_mv函数，直接跳到下一个环节去了。
现在一个大问题……
我把别人写好的源代码复制运行发现还是没有运行函数，但是没有报错
问题相关代码，请勿粘贴截图
from base64 import encode
from dataclasses import replace
from pandas import DataFrame
import requests
from lxml import etree
from bs4 import BeautifulSoup
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.102 Safari/537.36 Edg/104.0.1293.63"
}
start_num = [i for i in range(0,1,25)]
list_url_mv = []
for start in start_num:
url = "https://movie.douban.com/top250?start={}&filter=%22.format(start)
print("正在处理url:",url)
r = requests.get(url,headers=headers)
soup = BeautifulSoup(r.text,"html.parser")
url_mv_list = soup.select("#content > div > div.article > ol > li > div > div.info > div.hd > a ")
for index_url in range(len(url_mv_list)):
url_mv = url_mv_list[index_url]["href"]
list_url_mv.append(url_mv)
print(url_mv)
def loading_mv(url,number):
list_mv = []
print("-正在处理第{}部电影-".format(number+1))
list_mv.append(number+1)
response_mv = requests.get(url=url,headers=headers)
soup_mv = BeautifulSoup(response_mv.text,"html.parser")
mv_name = soup_mv.find_all('span',attrs={"property":"v:itemreviewed"})
mv_name = mv_name[0].get_text()
list_mv.append(mv_name)
mv_year = soup_mv.select("span.year")
mv_year = mv_year[0].get_text()[1:5]
list_mv.append(mv_year)
list_mv_director = []
mv_director = soup_mv.find_all('a',attrs={'rel':'v:directedBy'})
for director in mv_director:
list_mv_director.append(director.get_text())
string_director = '/'.join(list_mv_director)
list_mv_star = []
mv_star = soup_mv.find_all("a",attrs={"rel":"v:starring"})
if mv_star == []:
list_mv.append(None)
else:
mv_star = mv_star[0].get_text().strip('/')
mv_first_star = mv_star[0].split(":")
list_mv_star.append(mv_first_star[-1].strip())
# del mv_star[0]
for star in mv_star:
list_mv_star.append(star.strip())
string = '/'.join(list_mv_star)
list_mv.append(string)
list_mv_type = []
mv_type = soup_mv.find_all("a",attrs={"property":"v:genre"})
for type in mv_type:
list_mv_type.append(type.get_text())
string_type = '/'.join(list_mv_type)
list_mv.append(string_type)
mv_score = soup_mv.select("strong.ll.rating_num")
mv_score = mv_score[0].get_text()
list_mv.append(mv_score)
mv_evaluation = soup_mv.select("a.rating_people")
mv_evaluation = mv_evaluation[0].get_text().strip()
list_mv.append(mv_evaluation)
mv_plot = soup_mv.find_all("span",attrs={"class":"all hidden"})
if mv_plot == []:
list_mv.append(None)
else:
string_plot = mv_plot[0].get_text().strip().split()
new_string_plot = ' '.join(string_plot)
list_mv.append(new_string_plot)
list_mv.append(url)
return list_mv
list_all_mv = []
dict_mv_info = {}
for number in range(len(list_url_mv)):
mv_info = loading_mv(list_url_mv[number],number)
list_all_mv.append(mv_info)
print("-运行结束-")
pd = DataFrame(list_all_mv,columns=['电影排名','电影名称','电影导演','电影主演','电影类型','电影评分','评价人数','电影简介','电影链接'])
pd.to_excel(r'D:\Python\Python爬虫\豆瓣电影信息爬取\豆瓣电影前Top250.xlsx')
运行结果及报错内容
输出了空的表格
