使用Python获取爱奇艺电视剧弹幕数据的示例代码

import zlib
from bs4 import BeautifulSoup
with open(r"C:\Users\HP\Downloads\6024766870349300_300_10.z", 'rb') as fin:
 content = fin.read()
btArr = bytearray(content)
xml=zlib.decompress(btArr).decode('utf-8')
bs = BeautifulSoup(xml,"xml")
bs

import zlib
from bs4 import BeautifulSoup
import pandas as pd
import requests
def get_data(tv_name,tv_id):
 """
 获取每集的tvid
 :param tv_name: 集数，第1集、第2集...
 :param tv_id: 每集的tvid
 :return: DataFrame, 最终的数据
 """
 base_url = 'https://cmts.iqiyi.com/bullet/{}/{}/{}_300_{}.z'
 # 新建一个只有表头的DataFrame
 head_data = pd.DataFrame(columns=['uid','contentsId','contents','likeCount'])
 for i in range(1,20):
 url = base_url.format(tv_id[-4:-2],tv_id[-2:],tv_id,i)
 print(url)
 res = requests.get(url)
 if res.status_code == 200:
  btArr = bytearray(res.content) 
  xml=zlib.decompress(btArr).decode('utf-8') # 解压压缩文件
  bs = BeautifulSoup(xml,"xml") # BeautifulSoup网页解析
  data = pd.DataFrame(columns=['uid','contentsId','contents','likeCount'])
  data['uid'] = [i.text for i in bs.findAll('uid')]
  data['contentsId'] = [i.text for i in bs.findAll('contentId')]
  data['contents'] = [i.text for i in bs.findAll('content')]
  data['likeCount'] = [i.text for i in bs.findAll('likeCount')]
 else:
  break
 head_data = pd.concat([head_data,data],ignore_index = True)
 head_data['tv_name']= tv_name
 return head_data

from requests_html import HTMLSession, UserAgent
from bs4 import BeautifulSoup
import re
def get_tvid(url):
 """
 获取每集的tvid
 :param url: 请求网址
 :return: str, 每集的tvid
 """
 session = HTMLSession() #创建HTML会话对象
 user_agent = UserAgent().random #创建随机请求头
 header = {"User-Agent": user_agent}
 res = session.get(url, headers=header)
 res.encoding='utf-8'
 bs = BeautifulSoup(res.text,"html.parser")
 pattern =re.compile(".*?tvid.*?(\d{16}).*?") # 定义正则表达式
 text_list = bs.find_all(text=pattern) # 通过正则表达式获取内容
 for t in range(len(text_list)):
 res_list = pattern.findall(text_list[t])
 if not res_list:
  pass
 else:
  tvid = res_list[0]
 return tvid

def get_javascript0_links(url, class_name, class_name_father, sleep_time=0.02):
 """
 Selenium模拟用户点击爬取url
 :param url: 目标页面
 :param class_name: 模拟点击的类
 :param class_name_father： 模拟点击的类，此类为class_name的父类
 :param sleep_time: 留给页面后退的时间
 :return: list, 点击class为class_name进去的超链接
 """

 def wait(locator, timeout=15):
 """等到元素加载完成"""
 WebDriverWait(driver, timeout).until(EC.presence_of_element_located(locator))

 options = Options()
# options.add_argument("--headless") # 无界面,若你需要查看界面内容，可以将此行注释掉
 driver = webdriver.Chrome(options=options)
 driver.get(url)

 locator = (By.CLASS_NAME, class_name)
 wait(locator)
 element = driver.find_elements_by_class_name(class_name_father)
 elements = driver.find_elements_by_class_name(class_name)
 link = []
 linkNum = len(elements)
 for j in range(len(element)):
 wait(locator)
 driver.execute_script("arguments[0].click();", element[j]) # 模拟用户点击
 for i in range(linkNum):
  print(i)
  wait(locator)
  elements = driver.find_elements_by_class_name(class_name) # 再次获取元素，预防StaleElementReferenceException
  driver.execute_script("arguments[0].click();", elements[i]) # 模拟用户点击
  time.sleep(sleep_time)
  link.append(driver.current_url)
  time.sleep(sleep_time)
  driver.back()
 driver.quit()
 return link

if __name__ == "__main__":
 url = "https://www.iqiyi.com/v_1meaw5kgh3s.html"
 class_name = "qy-episode-num"
 link = get_javascript0_links(url, class_name, class_name_father="tab-bar")
 for i, _link in enumerate(link):
 print(i, _link)

def main(sleep_second=0.02):
 url = "https://www.iqiyi.com/v_1meaw5kgh3s.html"
 class_name = "select-item"
 class_name_father = "bar-li"
 links = get_javascript0_links(url, class_name, class_name_father)
 head_data = pd.DataFrame(columns=['tv_name','uid','contentsId','contents','likeCount'])
 for num, link in enumerate(links):
 tv_name = f"第{num+1}集"
 tv_id = get_tvid(url=link)
 data = get_data(tv_name,tv_id)
 head_data = pd.concat([head_data,data],ignore_index = True)
 time.sleep(sleep_second)
 return head_data

>>> data = main()
>>> data.info()
"""
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 246716 entries, 0 to 246715
Data columns (total 5 columns):
 # Column Non-Null Count Dtype 
--- ------ -------------- ----- 
 0 tv_name 246716 non-null object
 1 uid  246716 non-null object
 2 contentsId 246716 non-null object
 3 contents 246716 non-null object
 4 likeCount 246716 non-null object
dtypes: object(5)
memory usage: 9.4+ MB
"""
>>> data.sample(10)

def get_cut_words(content_series):
 """
 :param content_series: 需要分词的内容
 :return: list, 点击class为class_name进去的超链接
 """
 # 读入停用词表
 import jieba 
 stop_words = [] 
 with open("stop_words.txt", 'r', encoding='utf-8') as f:
 lines = f.readlines()
 for line in lines:
  stop_words.append(line.strip())
 # 添加关键词
 my_words = ['倪妮', '刘诗诗', '锁锁', '蒋三岁', '陈道明'] 
 for i in my_words:
 jieba.add_word(i) 
 # 自定义停用词
 my_stop_words = ['哈哈哈','哈哈哈哈', '真的'] 
 stop_words.extend(my_stop_words)  
 # 分词
 word_num = jieba.lcut(content_series.str.cat(sep='。'), cut_all=False)
 word_num_selected = [i for i in word_num if i not in stop_words and len(i)>=2] # 条件筛选
 
 return word_num_selected

import stylecloud
from IPython.display import Image 
text1 = get_cut_words(content_series=data.contents)
stylecloud.gen_stylecloud(text=' '.join(text1), collocations=False,
    font_path=r'‪C:\Windows\Fonts\msyh.ttc',
    icon_name='fas fa-rocket',size=400,
    output_name='流金岁月-词云.png')
Image(filename='流金岁月-词云.png')