from fake_useragent import UserAgent
import requests
from lxml import etree
from time import sleep


def get_html(url):
    '''
    :param url: 要爬取的地址
    :return: 返回html
    '''
    headers = {"User-Agent": UserAgent().chrome}
    resp = requests.get(url, headers=headers)
    sleep(2)                        #控制访问速度，以免给对方服务器造成负担，每次访问之前，睡上2秒
    if resp.status_code == 200:     #状态码==200即可返回
        resp.encoding = 'utf-8'
        return resp.text            #返回内容
    else:
        return None


def parse_list(html):
    '''
    :param html: 传递进来一个有电影列表的html
    :return: 返回一个电影列表的url
    '''

    e = etree.HTML(html)      #创建一个对象
    list_url = ['http://maoyan.com{}'.format(url) for url in e.xpath('/div[@class="channel-detail movie-item-title"]/a/@href')]
    return list_url


def pares_index(html):
    '''
    :param html: 传递进来一个有电影信息的html
    :return: 已经提取好的电影信息
    '''
    e = etree.HTML(html)
    name = e.xpath('//h1[@class="name"]/text()')[0]
    type = e.xpath('//li[@class="ellipsis"]/a[1]/text()')[0]
    actors = e.xpath('//div[@class="celebrity-group"][2]/ul[@class="celebrity-list clearfix"]/li/div/a/text()')
    actors = format_data(actors)
    return {"name": name, "type": type, "actors": actors}


def format_data(actors):                  #去重演员信息
    actor_set = set()
    for actor in actors:
        actor_set.add(actor.strip())      #strip()--去空格
    return actor_set


def main():
    num = int(input('请输要获取多少页：'))
    for page in range(num):
        url = 'https://maoyan.com/films?offset={}'.format(page * 30)

        list_html = get_html(url)
        list_url = parse_list(list_html)
        for url in list_url:
            info_html = get_html(url)       #发送新的请求获取电影信息
            movie = pares_index(info_html)  #解析电影信息
            print(movie)


if __name__ == '__main__':
    main()

老师，按照网站的最新链接修改xpath等各链接之后，只运行到页数，就结束了，到process finished with exit code 0,这是什么原因？

老师，我有个问题，正则如何匹配多个html相同的标签

而且我还抓了一个网页，有多个的span标签相同，这是不是意味要选择其他的筛选方法

老师为啥我使用streamlit模块时 报这个错误， 查看图片是正常的，

# _*_coding=utf-8 _*_
import streamlit as st
import cv2


def get_long():
    img1 = cv2.imread('./imgs/ctp1.png')
    img2 = cv2.imread('./imgs/ctp2.png')

    # 建立两个 st 控制的变量
    min_value = st.slider('input min value', max_value=500)
    max_value = st.slider('input max value', max_value=800)

    # 边缘化图片
    # Canny使用的滞后阈值，代阈值，高阈值
    canny1 = cv2.Canny(img1, min_value, max_value)

    # 保存图片
    # cv2.imwrite('./imgs/tstf.png', canny1)
    # 使用streamlit输出结果
    st.image(canny1)
    st.write(canny1)

    canny2 = cv2.Canny(img2, min_value, max_value)
    st.image(canny2)
    st.write(canny2)


if __name__ == '__main__':
    get_long()

老师这个问题怎么解决

我这个扩展程序的设置界面打不开是啥情况，麻烦老师指点一下

2020-03-14 16:33:59 [scrapy.utils.log] INFO: Scrapy 2.0.0 started (bot: rockstone)
2020-03-14 16:33:59 [scrapy.utils.log] INFO: Versions: lxml 4.5.0.0, libxml2 2.9.5, cssselect 1.1.0, parsel 1.5.2, w3lib 1.21.0, Twisted 19.10.0, Python 3.7.6 (tags/v3.7.6:43364
a7ae0, Dec 19 2019, 00:42:30) [MSC v.1916 64 bit (AMD64)], pyOpenSSL 19.1.0 (OpenSSL 1.1.1d  10 Sep 2019), cryptography 2.8, Platform Windows-10-10.0.18362-SP0
2020-03-14 16:33:59 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.selectreactor.SelectReactor
2020-03-14 16:33:59 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'rockstone',
 'NEWSPIDER_MODULE': 'rockstone.spiders',
 'ROBOTSTXT_OBEY': True,
 'SPIDER_MODULES': ['rockstone.spiders']}
2020-03-14 16:33:59 [scrapy.extensions.telnet] INFO: Telnet Password: 12ce7d6c067a2499
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
 'scrapy.extensions.telnet.TelnetConsole',
 'scrapy.extensions.logstats.LogStats']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
 'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
 'scrapy.downloadermiddlewares.retry.RetryMiddleware',
 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
 'scrapy.downloadermiddlewares.stats.DownloaderStats']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
 'scrapy.spidermiddlewares.referer.RefererMiddleware',
 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
 'scrapy.spidermiddlewares.depth.DepthMiddleware']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Spider opened
2020-03-14 16:33:59 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2020-03-14 16:33:59 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2020-03-14 16:33:59 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://www.baidu.com/robots.txt> (referer: None)
2020-03-14 16:33:59 [scrapy.downloadermiddlewares.robotstxt] DEBUG: Forbidden by robots.txt: <GET http://www.baidu.com/>
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Closing spider (finished)
2020-03-14 16:33:59 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/exception_count': 1,
 'downloader/exception_type_count/scrapy.exceptions.IgnoreRequest': 1,
 'downloader/request_bytes': 223,
 'downloader/request_count': 1,
 'downloader/request_method_count/GET': 1,
 'downloader/response_bytes': 676,
 'downloader/response_count': 1,
 'downloader/response_status_count/200': 1,
 'elapsed_time_seconds': 0.350322,
 'finish_reason': 'finished',
 'finish_time': datetime.datetime(2020, 3, 14, 8, 33, 59, 677262),
 'log_count/DEBUG': 2,
 'log_count/INFO': 10,
 'response_received_count': 1,
 'robotstxt/forbidden': 1,
 'robotstxt/request_count': 1,
 'robotstxt/response_count': 1,
 'robotstxt/response_status_count/200': 1,
 'scheduler/dequeued': 1,
 'scheduler/dequeued/memory': 1,
 'scheduler/enqueued': 1,
 'scheduler/enqueued/memory': 1,
 'start_time': datetime.datetime(2020, 3, 14, 8, 33, 59, 326940)}
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Spider closed (finished)

老师 我这个按照百度那个测试     没有返回的html信息

老师，猫眼电影页面的观看人数提取不出来，爬取的结果中’人想看‘前面的数字也显示不出来，第二次再爬取的时候直接被它的反爬给干掉了

源码：

老师，我的data里还有一个参数，我用同样的方法增加参数传进去，执行没报错，但好像也没登录成功字样。另外，地址栏输入的网址和Requset URL的地址完全不一样，如下图

地址栏的是http://IP地址/webpages/login.html

问题如下：

Mongo下载老是失败，能不能发一下老师的安装包

出现了这样的问题，老师该怎么解决

不管是用最新的19.7.0的版本还是用视频里面的17.0.1的版本都出现了这样的问题

对于像虎牙这种直播网，点击下一页后，url不变，多线程爬取又该如何实现呢？？？

1、老师，这种滑块的验证如何登陆啊？

2、老师您帮忙看看我的这个代码是不是没有进入用户登录啊？

from fake_useragent import UserAgent
import requests

login_url = ""https://www.xiami.com/api/passport/login?_s=1c4b8c7df073c5f5d87c8c3d53696a80&_xm_cf_=8AbWYVbpKjqiKTOieajzdtRP""
headers = {"user-agent": UserAgent().random}
form_data ={
    "account":"18233301608",
    "ncoSessionid":"01l226v1bCklKZGaS4pM-XkexAHIXQJKMkheIWOYlE-tp_FJVxBE0fkn51blEkQ8qSFiRJRrODbFWU2wA-FVg4l6_ijMiHM99ATKr2LD2tbEEoswFpbuRk3JI-nSWcLf2TONkhHRXe2HqoHRrsLwwAbGyPlBJUEqctiaTooWaXr7I",
    "ncoSign":"05hsU0UmHVD-ozk047zGZbWfzLuhtVMjb_10CvaRGXwXl10MXSzcF_9bE2GGvgVMDdifepMAnw6Rn_2tZT3WyrGLbBKxgl_0DDEi7N56zYCUKS7gg10a799K-ucg9hOXJiiTxxvDz1Ns8gQI1KNIiNJv-VYFHHErD-4gmlRFljyr-5T5579_esKza3q0GSpobljee0w8cxy3tEkSiNuHss76-tYYvMzxGJ8sWhufa08AGlyrW3-ss0BQaY8rOV2-hO7M2RN7TqY7ZdyATDqxDvVrLFKnJHrkyqMPlCArpTVwisPzBSv0cO0KaYvsX8NsDgl8IFdMjyllNGeqO6_D5seeQrUv7a3LC_fnQlND7tPqWpOWDjUdnNbDHrufWtFPWq2PeK_y1yCIpd2N2lT0RgHg",
    "ncoToken":"web_login_1564373329605_0.958661482699025",
    "password":"e10adc3949ba59abbe56e057f20f883e"
}
session = requests.Session()
resp = session.post(login_url,data=form_data,headers=headers)
resp.encoding = 'utf-8'
print(resp.text)

怎么样修改下代码才可以正确用户登录呢？

3、

http类型的ip能访问https 的网页吗？

https类型的IP能访问http的网页吗？

如果一个页面并没有弹出框的提示，那么设置这个函数会不会卡住，反过来，如果不会卡住，那么我是不是可以在所有的应用场合都可以运用这个函数，确定我的代码的稳定性？

2020-03-14 16:33:59 [scrapy.utils.log] INFO: Scrapy 2.0.0 started (bot: rockstone)
2020-03-14 16:33:59 [scrapy.utils.log] INFO: Versions: lxml 4.5.0.0, libxml2 2.9.5, cssselect 1.1.0, parsel 1.5.2, w3lib 1.21.0, Twisted 19.10.0, Python 3.7.6 (tags/v3.7.6:43364
a7ae0, Dec 19 2019, 00:42:30) [MSC v.1916 64 bit (AMD64)], pyOpenSSL 19.1.0 (OpenSSL 1.1.1d  10 Sep 2019), cryptography 2.8, Platform Windows-10-10.0.18362-SP0
2020-03-14 16:33:59 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.selectreactor.SelectReactor
2020-03-14 16:33:59 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'rockstone',
 'NEWSPIDER_MODULE': 'rockstone.spiders',
 'ROBOTSTXT_OBEY': True,
 'SPIDER_MODULES': ['rockstone.spiders']}
2020-03-14 16:33:59 [scrapy.extensions.telnet] INFO: Telnet Password: 12ce7d6c067a2499
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
 'scrapy.extensions.telnet.TelnetConsole',
 'scrapy.extensions.logstats.LogStats']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
 'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
 'scrapy.downloadermiddlewares.retry.RetryMiddleware',
 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
 'scrapy.downloadermiddlewares.stats.DownloaderStats']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
 'scrapy.spidermiddlewares.referer.RefererMiddleware',
 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
 'scrapy.spidermiddlewares.depth.DepthMiddleware']
2020-03-14 16:33:59 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Spider opened
2020-03-14 16:33:59 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2020-03-14 16:33:59 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2020-03-14 16:33:59 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://www.baidu.com/robots.txt> (referer: None)
2020-03-14 16:33:59 [scrapy.downloadermiddlewares.robotstxt] DEBUG: Forbidden by robots.txt: <GET http://www.baidu.com/>
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Closing spider (finished)
2020-03-14 16:33:59 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/exception_count': 1,
 'downloader/exception_type_count/scrapy.exceptions.IgnoreRequest': 1,
 'downloader/request_bytes': 223,
 'downloader/request_count': 1,
 'downloader/request_method_count/GET': 1,
 'downloader/response_bytes': 676,
 'downloader/response_count': 1,
 'downloader/response_status_count/200': 1,
 'elapsed_time_seconds': 0.350322,
 'finish_reason': 'finished',
 'finish_time': datetime.datetime(2020, 3, 14, 8, 33, 59, 677262),
 'log_count/DEBUG': 2,
 'log_count/INFO': 10,
 'response_received_count': 1,
 'robotstxt/forbidden': 1,
 'robotstxt/request_count': 1,
 'robotstxt/response_count': 1,
 'robotstxt/response_status_count/200': 1,
 'scheduler/dequeued': 1,
 'scheduler/dequeued/memory': 1,
 'scheduler/enqueued': 1,
 'scheduler/enqueued/memory': 1,
 'start_time': datetime.datetime(2020, 3, 14, 8, 33, 59, 326940)}
2020-03-14 16:33:59 [scrapy.core.engine] INFO: Spider closed (finished)

老师 我这个按照百度那个测试     没有返回的html信息