使用Python爬取携程旅游游记文章

简介

本文介绍了使用Python编写的爬虫代码，用于爬取携程旅游网站上的游记文章。通过该代码，可以获取游记的标题、内容、天数、时间、和谁一起以及玩法等信息

导入所需的库

首先，我们需要导入所需的库，包括re、BeautifulSoup、bag、easygui和webbrowser。其中，re库用于正则表达式匹配，BeautifulSoup库用于解析HTML页面，bag库用于创建会话，easygui库用于显示错误信息，webbrowser库用于打开验证码验证页面。

python 复制代码

import re
from bs4 import BeautifulSoup
import bag
import easygui
import webbrowser
import time

创建会话并设置请求头和cookies信息

python 复制代码

session = bag.session.create_session()
session.headers['Referer'] = r'https://you.ctrip.com/travels/'
session.get(r'https://you.ctrip.com/TravelSite/Home/IndexTravelListHtml?p=2&Idea=0&Type=100&Plate=0')
session.cookies[''] = r"你的cookies"

定义主函数main()，在其中调用catch函数并打印结果

python 复制代码

def main():
    resp = catch(r'https://you.ctrip.com/travels/qinhuangdao132/4011655.html')
    print(resp)

定义show_error_message函数，用于显示错误信息，并提供一个验证按钮以打开验证码验证页面

python 复制代码

def show_error_message(error):
    choices = ["验证"]
    button_box_choice = easygui.buttonbox(error, choices=choices)
    if button_box_choice == "验证":
        webbrowser.open("https://verify.ctrip.com/static/ctripVerify.html?returnUrl=https%3A%2F%2Fyou.ctrip.com%2Ftravelsite%2Ftravels%2Fshanhaiguan120556%2F3700092.html&bgref=l2j65wlGQDYtmBZjKEoy5w%3D%3D")

定义catch函数，用于解析游记文章页面并提取相关信息

python 复制代码

def catch(url) -> list:
    result_ = []
    try:
        resp = session.get(url)
        resp.encoding = 'utf8'
        resp.close()
        time.sleep(2)
        html = BeautifulSoup(resp.text, 'lxml')
        # 省略部分代码
        return result_
    except Exception as e:
        show_error_message(e)
        time.sleep(10)
        catch(url)

完整代码

python 复制代码

#!/usr/bin/env python3
# coding:utf-8
import re
from bs4 import BeautifulSoup
import bag
import easygui
import webbrowser
import time

session = bag.session.create_session()
session.headers['Referer'] = r'https://you.ctrip.com/travels/'
session.get(r'https://you.ctrip.com/TravelSite/Home/IndexTravelListHtml?p=2&Idea=0&Type=100&Plate=0')
session.cookies[
    ''] = r"你的cookies"


# noinspection PyBroadException
def main():
    resp = catch(r'https://you.ctrip.com/travels/qinhuangdao132/4011655.html')
    print(resp)


def show_error_message(error):
    choices = ["验证"]
    button_box_choice = easygui.buttonbox(error, choices=choices)
    if button_box_choice == "验证":
        webbrowser.open(
            "https://verify.ctrip.com/static/ctripVerify.html?returnUrl=https%3A%2F%2Fyou.ctrip.com%2Ftravelsite%2Ftravels%2Fshanhaiguan120556%2F3700092.html&bgref=l2j65wlGQDYtmBZjKEoy5w%3D%3D")


def catch(url) -> list:
    result_ = []
    try:
        resp = session.get(url)
        resp.encoding = 'utf8'
        resp.close()
        time.sleep(2)
        # print(resp.text)
        html = BeautifulSoup(resp.text, 'lxml')
        title = re.findall(r'<h1 class="title1">(.*?)</h1>', resp.text)
        if len(title) == 0:
            title = html.find_all('div', class_="ctd_head_left")[0].h2.text
        soup = html.find_all('div', class_="ctd_content")
        days = re.compile(r'<span><i class="days"></i>天数：(.*?)</span>', re.S)
        times = re.compile(r'<span><i class="times"></i>时间：(.*?)</span>', re.S)
        whos = re.compile(r'<span><i class="whos"></i>和谁：(.*?)</span>', re.S)
        plays = re.compile(r'<span><i class="plays"></i>玩法：(.*?)</span>', re.S)
        content = re.compile(r'<h3>.*?发表于.*?</h3>(.*?)</div>]', re.S)
        mid = []
        for info in re.findall(r'<p>(.*?)</p>', str(re.findall(content, str(soup)))):
            if info == '':
                pass
            else:
                mid.append(re.sub(r'<.*?>', '', info))
        if len(mid) == 0:
            for info in re.findall(r'<p>(.*?)</p>', str(soup)):
                if info == '':
                    pass
                else:
                    mid.append(re.sub(r'<.*?>', '', info))
        result_.append([
            ''.join(title).strip(),
            '\n'.join(mid),
            ''.join(re.findall(days, str(soup))).replace(' ', ''),
            ''.join(re.findall(times, str(soup))).replace(' ', ''),
            ''.join(re.findall(whos, str(soup))),
            ''.join(re.findall(plays, str(soup))),
            url
        ])
        return result_
    except Exception as e:
        show_error_message(e)
        time.sleep(10)
        catch(url)


if __name__ == '__main__':
    main()

运行结果

结语

如果你觉得本教程对你有所帮助，不妨点赞并关注我的CSDN账号。我会持续为大家带来更多有趣且实用的教程和资源。谢谢大家的支持！