python3：爬取的内容包含中文，输出后乱码的问题

Posted 2021-03-17 若岁月轻狂，愿你可以笑看夕阳

爬取的内容包含中文，输出后乱码的问题

需求：想要实现这样的功能：用户输入喜欢的电影名字，程序即可在电影天堂https://www.ygdy8.com爬取电影所对应的下载链接，并将下载链接打印出来

遇到的问题：获取磁力的链接中包含中文，打印出来后乱码

 

解决办法：手动指定编码方式：

if res.encoding == \'ISO-8859-1\':
    encodings = requests.utils.get_encodings_from_content(res.text)
    if encodings:
        encoding = encodings[0]
    else:
        encoding = res.apparent_encoding
else:
    encoding = res.encoding
encode_content = res.content.decode(encoding, \'replace\').encode(\'utf-8\', \'replace\')

 

# 想要实现这样的功能：用户输入喜欢的电影名字，程序即可在电影天堂https://www.ygdy8.com爬取电影所对应的下载链接，并将下载链接打印出来

import requests
from bs4 import BeautifulSoup
from urllib.request import pathname2url

# 为躲避反爬机制，伪装成浏览器的请求头
headers = {\'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36 OPR/65.0.3467.78 (Edition Baidu)\'}

# 获取电影磁力链接
def getMovieDownloadLink(filmlink):
    res = requests.get(filmlink, headers=headers)
    if res.status_code == 200:

        # 请求后的内容中文乱码处理办法：
        # 当response编码是‘ISO-8859-1’，我们应该首先查找response header设置的编码；如果此编码不存在，查看返回的Html的header设置的编码
        if res.encoding == \'ISO-8859-1\':
            encodings = requests.utils.get_encodings_from_content(res.text)
            if encodings:
                encoding = encodings[0]
            else:
                encoding = res.apparent_encoding
        else:
            encoding = res.encoding
        encode_content = res.content.decode(encoding, \'replace\').encode(\'utf-8\', \'replace\')

        soup = BeautifulSoup(encode_content, \'html.parser\')
        Zoom = soup.select_one(\'#Zoom\')
        fileurl = Zoom.find(\'table\').find(\'a\').text
        with open(\'./17-电影天堂磁力.txt\',\'a\', newline=\'\') as file:
            file.write(fileurl + \'\\n\')

    else:
        print(\'电影链接：{}请求失败！\'.format(filmlink))

def main():
    dyurl = \'https://www.ygdy8.com\'
    # movie = input(\'请输入电影名称：\')
    movie = \'沉睡魔咒\'
    movie = movie.encode(\'gbk\')
    url = \'http://s.ygdy8.com/plus/s0.php?typeid=1&keyword={0}\'.format(pathname2url(movie))
    res = requests.get(url, headers=headers)
    if res.status_code == 200:
        htmltext = res.text
        soup = BeautifulSoup(htmltext, \'html.parser\')
        co_content8 = soup.find(\'div\', class_=\'co_content8\')
        tables = co_content8.find(\'ul\').find_all(\'table\')
        if len(tables) <= 0:
            print(\'没有找到相关的资源，可到站点上搜索 {0}\'.format(dyurl))
        else:
            for table in tables:
                filmlink = dyurl + table.find(\'a\')[\'href\']
                getMovieDownloadLink(filmlink)

    else:
        print(\'请求失败！\')

main()

结果：

参考：

https://blog.csdn.net/guoxinian/article/details/82978067

http://blog.csdn.net/a491057947/article/details/47292923

http://docs.python-requests.org/en/latest/user/quickstart/#response-content