dow 发表于 2020-12-21 23:30:35

豆瓣top250求救

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; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/57.0.2987.95 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:
      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
    return int(depth)

def main():
    host = "http://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.append(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()

到底是咋回事，这个下面的问题

    if_ _name_ _ == "_ _main_ _":
             ^
SyntaxError: invalid syntax

Sebass 发表于 2020-12-22 09:51:32

兄嘚，SyntaxError 最最最最最常见的是你用了中文符号{:5_104:}

z5560636 发表于 2020-12-22 10:43:16

if _ _name_ _ == "_ _main_ _":
if后面少了一个空格、
if __name__ == "__main__":

情绪z 发表于 2020-12-22 10:43:25

if __name__ == '__main__':

逃兵 发表于 2020-12-22 11:10:57

代码错误挺多
看一下源码
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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 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)

    # 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

    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()

第十行res = requests,get(url, headers = headers)改成res = requests.get(url, headers = headers)
第二十三行之后抄错行了
# 资料的部分和#评分的部分抄混了，代码逻辑就乱套了
第56行if_ _name_ _ == "_ _main_ _": 改为 if __name__ == "__main__":
页: [1]
查看完整版本: 豆瓣top250求救