版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
本文链接:https://blog.csdn.net/weixin_40313634/article/details/96611824
爬取过程中的问题解决
代码语言:javascript复制环境 :Windows Python 3.7 selenium
1. class 中含有空格,如何定位
代码语言:javascript复制 <div class="u-cover u-cover-1">
代码语言:javascript复制 browser.find_elements_by_css_selector('[class = "u-cover u-cover-1"]')
2. 定位信息好着,就是获取不到元素
代码语言:javascript复制原因:
selenium 打开网页后, 默认是在父级 Frame 里, 直接搜索是搜不到子 Frame 里的信息的。
需要切换 Frame。
方法:
switch_to.frame('frameid')
switch_to.parent_frame()
- 类似问题
原因:点击后,浏览器新打开了个选项卡。没有切换过来,导致还是在旧的选项卡里查找
解决:
browser.switch_to_window(browser.window_handles[1])
- 例子如下
<iframe name="contentFrame" id="g_iframe" class="g-iframe" scrolling="auto" frameborder="0" src="about:blank" allowfullscreen="true"></iframe>
代码语言:javascript复制 browser.switch_to.frame('g_iframe')
3. find_elements后点击不了抓取的元素
- 问题: for 循环执行第二次时报错如下:
selenium.common.exceptions.StaleElementReferenceException: Message: stale element reference: element is not attached to the page document
- 代码
we_gedans = self.browser.find_elements_by_css_selector('[class = "u-cover u-cover-1"]')
for we_gedan in we_gedans:
we_gedan.click()
- 原因
官方给出解释如下:
The element has been deleted entirely.
The element is no longer attached to the DOM.
就是页面元素过期,引用的元素过时,不再依附于当前页面,需要重新定位获取元素对象
find_elements 查找到的是 WebElement 类型的数组数据,含有元素在当前页面的地址信息,调用 click() 方法就是使用了此地址信息。
切换页面后,此地址信息就失效了。所以不能在直接在循环中调用 click()
4. eyed3 pip 安装成功, import报错
- 报错如下
import magic
File "C:UserszuoyAppDataLocalProgramsPythonPython37libsite-packagesmagic.py", line 181, in <module>
raise ImportError('failed to find libmagic. Check your installation')
ImportError: failed to find libmagic. Check your installation
- 原因: eyed3 依赖 magic,必须安装上这个才能使用
pip install pip install python-magic-bin
pip install eyed3
代码
代码语言:javascript复制#!/usr/bin/env python
'''
功能:访问网易云音乐网站,下载歌单里的所有免费歌曲
时间:2019/07/20
'''
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
import requests
import eyed3 # 给下载的MP3歌曲添加属性信息:专辑名、歌手等
import time
import json
import os
class Splider(object):
def __init__(self):
self.__url = 'https://music.163.com/'
self.browser = webdriver.Chrome()
def __get_gedans(self, url=None):
gedans = []
self.browser.get(self.__url)
self.browser.switch_to.frame('g_iframe')
we_gedans = self.browser.find_elements_by_css_selector('[class = "u-cover u-cover-1"]')
for we_gedan in we_gedans:
gedan = {}
gedan = {
'title': we_gedan.find_element_by_css_selector('a').get_attribute('title'),
'url': we_gedan.find_element_by_css_selector('a').get_attribute('href'),
'image': we_gedan.find_element_by_css_selector('img').get_attribute('src'),
'click': we_gedan.find_element_by_css_selector('.nb').text
}
gedans.append(gedan)
return gedans
def __get_songs(self, gedan):
urls = []
self.browser.get(gedan['url'])
self.browser.switch_to.frame('g_iframe')
we_songs = self.browser.find_elements_by_css_selector('[class = "even "]')
for we_song in we_songs:
url = {
'id': we_song.find_element_by_css_selector('.left .hd span').get_attribute('data-res-id'),
'name': we_song.find_element_by_css_selector('.f-cb b').get_attribute('title'),
'songer': we_song.find_elements_by_css_selector('.text')[0].get_attribute('title'),
'cd': we_song.find_elements_by_css_selector('.text')[1].find_element_by_css_selector('a').get_attribute('title')
}
# 清理掉其中的非显示字符
for key, value in url.items():
url[key] = ' '.join(value.split())
urls.append(url)
return urls
def __download_song(self, song):
base_url = "http://music.163.com/song/media/outer/url?id={0}"
url = base_url.format(song['id'])
re = requests.get(url)
if re.status_code == 200:
filename = song['name'] '.mp3'
with open(filename, 'wb') as f:
f.write(re.content)
at_song = eyed3.load(filename)
at_song.tag.artist = song['songer']
at_song.tag.album = song['cd']
at_song.tag.title = song['name']
at_song.tag.save()
return
def __save_json(self, strs, filename):
filename = filename if os.path.splitext(filename)[1] == '.json' else os.path.splitext(filename)[0] '.json'
with open(filename, 'w', encoding='utf-8') as f:
f.write(json.dumps(strs, indent=4, ensure_ascii=False))
def __read_json(self, filename):
data = []
filename = filename if os.path.splitext(filename)[1] == '.json' else os.path.splitext(filename)[0] '.json'
with open(filename, 'r', encoding='utf-8') as f:
data = json.loads(f.read())
return data
def run(self):
gedans = self.__get_gedans()
self.__save_json(gedans, 'gedans.json')
for gedan in gedans:
try:
songs = self.__get_songs(gedan)
self.__save_json(songs, 'songs.json')
except Exception as e:
print(e.args)
os.chdir('songs')
for song in songs:
try:
self.__download_song(song)
except Exception as e:
print(e.args)
os.chdir('..')
self.browser.close()
if __name__ == '__main__':
splider = Splider()
splider.run()