c451995951 发表于 2020-7-2 17:20:19

爬虫爬出来没有内容

import requests
import bs4
import re


def open_url(url):
    # 使用代理防止被反爬虫禁止
    # 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", calss_="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()

c451995951 发表于 2020-7-2 17:40:46

求大佬救救

wp231957 发表于 2020-7-2 17:53:26

c451995951 发表于 2020-7-2 17:40
求大佬救救

使用本机做代理，哪个教的

qiuyouzhi 发表于 2020-7-2 17:56:21

太粗心了
targets = soup.find_all("div", calss_="hd")
class_ 写成了 calss_ ？
改成这样就行了

import requests
import bs4
import re


def open_url(url):
    # 使用代理防止被反爬虫禁止
    # 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()
页: [1]
查看完整版本: 爬虫爬出来没有内容