python - 如何使用 python 3.6 从维基百科类别的所有关联页面中抓取和提取所有子类别名称？

Question

我想抓取类别页面类别标题下的所有子类别和页面:“Category:Computer science”。其链接如下:http://en.wikipedia.org/wiki/Category:Computer_science .

我从以下链接中指定的以下堆栈溢出答案中得到了关于上述问题的想法。 Pythonic beautifulSoup4 : How to get remaining titles from the next page link of a wikipedia category和 How to scrape Subcategories and pages in categories of a Category wikipedia page using Python

但是，答案并没有完全解决问题。它只抓取类别“计算机科学”中的页面。但是，我想提取所有子类别名称及其相关页面。我希望流程应该以深度为 10 的 BFS 方式报告结果。有什么办法可以做到这一点吗？

我从 this linked post 中找到了以下代码:

from pprint import pprint
from urllib.parse import urljoin

from bs4 import BeautifulSoup
import requests


base_url = 'https://en.wikipedia.org/wiki/Category:Computer science'


def get_next_link(soup):
    return soup.find("a", text="next page")

def extract_links(soup):
    return [a['title'] for a in soup.select("#mw-pages li a")]


with requests.Session() as session:
    content = session.get(base_url).content
    soup = BeautifulSoup(content, 'lxml')

    links = extract_links(soup)
    next_link = get_next_link(soup)
    while next_link is not None:  # while there is a Next Page link
        url = urljoin(base_url, next_link['href'])
        content = session.get(url).content
        soup = BeautifulSoup(content, 'lxml')

        links += extract_links(soup)

        next_link = get_next_link(soup)

pprint(links)

Answer 1

要抓取子类别，您必须使用 selenium与下拉菜单进行交互。对第二类链接的简单遍历将生成页面，但是，要找到所有子类别，需要递归以正确分组数据。下面的代码使用了 breadth-first search 的一个简单变体。确定何时停止遍历在 while 循环的每次迭代中生成的下拉切换对象:

from selenium import webdriver
import time
from bs4 import BeautifulSoup as soup 
def block_data(_d):
  return {_d.find('h3').text:[[i.a.attrs.get('title'), i.a.attrs.get('href')] for i in _d.find('ul').find_all('li')]}

def get_pages(source:str) -> dict:
  return [block_data(i) for i in soup(source, 'html.parser').find('div', {'id':'mw-pages'}).find_all('div', {'class':'mw-category-group'})]

d = webdriver.Chrome('/path/to/chromedriver')
d.get('https://en.wikipedia.org/wiki/Category:Computer_science')
all_pages = get_pages(d.page_source)
_seen_categories = []
def get_categories(source):
  return [[i['href'], i.text] for i in soup(source, 'html.parser').find_all('a', {'class':'CategoryTreeLabel'})]

def total_depth(c):
  return sum(1 if len(b) ==1 and not b[0] else sum([total_depth(i) for i in b]) for a, b in c.items())

def group_categories(source) -> dict:
  return {i.find('div', {'class':'CategoryTreeItem'}).a.text:(lambda x:None if not x else [group_categories(c) for c in x])(i.find_all('div', {'class':'CategoryTreeChildren'})) for i in source.find_all('div', {'class':'CategoryTreeSection'})}

while True:
  full_dict = group_categories(soup(d.page_source, 'html.parser'))
  flag = False
  for i in d.find_elements_by_class_name('CategoryTreeToggle'):
     try:
       if i.get_attribute('data-ct-title') not in _seen_categories:
          i.click()
          flag = True
          time.sleep(1)
     except:
       pass
     else:
       _seen_categories.append(i.get_attribute('data-ct-title'))
  if not flag:
     break

---

输出:

所有页面:

[{'\xa0': [['Computer science', '/wiki/Computer_science'], ['Glossary of computer science', '/wiki/Glossary_of_computer_science'], ['Outline of computer science', '/wiki/Outline_of_computer_science']]}, 
 {'B': [['Patrick Baudisch', '/wiki/Patrick_Baudisch'], ['Boolean', '/wiki/Boolean'], ['Business software', '/wiki/Business_software']]}, 
 {'C': [['Nigel A. L. Clarke', '/wiki/Nigel_A._L._Clarke'], ['CLEVER score', '/wiki/CLEVER_score'], ['Computational human modeling', '/wiki/Computational_human_modeling'], ['Computational social choice', '/wiki/Computational_social_choice'], ['Computer engineering', '/wiki/Computer_engineering'], ['Critical code studies', '/wiki/Critical_code_studies']]}, 
  {'I': [['Information and computer science', '/wiki/Information_and_computer_science'], ['Instance selection', '/wiki/Instance_selection'], ['Internet Research (journal)', '/wiki/Internet_Research_(journal)']]}, 
  {'J': [['Jaro–Winkler distance', '/wiki/Jaro%E2%80%93Winkler_distance'], ['User:JUehV/sandbox', '/wiki/User:JUehV/sandbox']]}, 
  {'K': [['Krauss matching wildcards algorithm', '/wiki/Krauss_matching_wildcards_algorithm']]}, 
  {'L': [['Lempel-Ziv complexity', '/wiki/Lempel-Ziv_complexity'], ['Literal (computer programming)', '/wiki/Literal_(computer_programming)']]}, 
  {'M': [['Machine learning in bioinformatics', '/wiki/Machine_learning_in_bioinformatics'], ['Matching wildcards', '/wiki/Matching_wildcards'], ['Sidney Michaelson', '/wiki/Sidney_Michaelson']]}, 
  {'N': [['Nuclear computation', '/wiki/Nuclear_computation']]}, {'O': [['OpenCV', '/wiki/OpenCV']]}, 
  {'P': [['Philosophy of computer science', '/wiki/Philosophy_of_computer_science'], ['Prefetching', '/wiki/Prefetching'], ['Programmer', '/wiki/Programmer']]}, 
  {'Q': [['Quaject', '/wiki/Quaject'], ['Quantum image processing', '/wiki/Quantum_image_processing']]}, 
  {'R': [['Reduction Operator', '/wiki/Reduction_Operator']]}, {'S': [['Social cloud computing', '/wiki/Social_cloud_computing'], ['Software', '/wiki/Software'], ['Computer science in sport', '/wiki/Computer_science_in_sport'], ['Supnick matrix', '/wiki/Supnick_matrix'], ['Symbolic execution', '/wiki/Symbolic_execution']]}, 
  {'T': [['Technology transfer in computer science', '/wiki/Technology_transfer_in_computer_science'], ['Trace Cache', '/wiki/Trace_Cache'], ['Transition (computer science)', '/wiki/Transition_(computer_science)']]}, 
  {'V': [['Viola–Jones object detection framework', '/wiki/Viola%E2%80%93Jones_object_detection_framework'], ['Virtual environment', '/wiki/Virtual_environment'], ['Visual computing', '/wiki/Visual_computing']]}, 
  {'W': [['Wiener connector', '/wiki/Wiener_connector']]}, 
  {'Z': [['Wojciech Zaremba', '/wiki/Wojciech_Zaremba']]}, 
  {'Ρ': [['Portal:Computer science', '/wiki/Portal:Computer_science']]}]

full_dict 非常大，由于它的大小，我无法将它完整地张贴在这里，但是，下面是一个函数的实现，用于遍历结构并选择所有元素直到深度十:

def trim_data(d, depth, count):
   return {a:None if count == depth else [trim_data(i, depth, count+1) for i in b] for a, b in d.items()}

final_subcategories = trim_data(full_dict, 10, 0)

编辑:从树上移除叶子的脚本:

def remove_empty_children(d):
  return {a:None if len(b) == 1 and not b[0] else 
     [remove_empty_children(i) for i in b if i] for a, b in d.items()}

运行上述时:

c = {'Areas of computer science': [{'Algorithms and data structures': [{'Abstract data types': [{'Priority queues': [{'Heaps (data structures)': [{}]}, {}], 'Heaps (data structures)': [{}]}]}]}]}
d = remove_empty_children(c)

输出:

{'Areas of computer science': [{'Algorithms and data structures': [{'Abstract data types': [{'Priority queues': [{'Heaps (data structures)': None}], 'Heaps (data structures)': None}]}]}]}

编辑 2:展平整个结构:

def flatten_groups(d):
   for a, b in d.items():
     yield a
     if b is not None:
        for i in map(flatten_groups, b):
           yield from i


print(list(flatten_groups(remove_empty_children(c))))

输出:

['Areas of computer science', 'Algorithms and data structures', 'Abstract data types', 'Priority queues', 'Heaps (data structures)', 'Heaps (data structures)']

编辑 3:

要访问特定级别的每个子类别的所有页面，可以使用原始的 get_pages 函数和略有不同版本的 group_categories 方法

def _group_categories(source) -> dict:
  return {i.find('div', {'class':'CategoryTreeItem'}).find('a')['href']:(lambda x:None if not x else [group_categories(c) for c in x])(i.find_all('div', {'class':'CategoryTreeChildren'})) for i in source.find_all('div', {'class':'CategoryTreeSection'})}
from collections import namedtuple
page = namedtuple('page', ['pages', 'children'])
def subcategory_pages(d, depth, current = 0):
  r = {} 
  for a, b in d.items():
     all_pages_listing = get_pages(requests.get(f'https://en.wikipedia.org{a}').text)
     print(f'page number for {a}: {len(all_pages_listing)}')
     r[a] = page(all_pages_listing, None if current==depth else [subcategory_pages(i, depth, current+1) for i in b])
  return r


print(subcategory_pages(full_dict, 2))

请注意，为了使用 subcategory_pages，必须使用 _group_categories 代替 group_categories。