import sqlite3<\/p>\nimport requests<\/p>\n
def create_table():<\/p>\n
conn = sqlite3.connect('zhihu.db')<\/p>\n
cursor = conn.cursor()<\/p>\n
cursor.execute('''CREATE TABLE IF NOT EXISTS answers<\/p>\n
(id INTEGER PRIMARY KEY,<\/p>\n
content TEXT)''')<\/p>\n
conn.commit()<\/p>\n
conn.close()<\/p>\n
def insert_answer(content):<\/p>\n
conn = sqlite3.connect('zhihu.db')<\/p>\n
cursor = conn.cursor()<\/p>\n
cursor.execute("INSERT INTO answers (content) VALUES (?)", (content,))<\/p>\n
conn.commit()<\/p>\n
conn.close()<\/p>\n
def get_answers(question_id, offset=0, limit=20):<\/p>\n
url = f'https:\/\/www.zhihu.com\/api\/v4\/questions\/{question_id}\/answers'<\/p>\n
headers = {<\/p>\n
'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36'<\/p>\n
}<\/p>\n
params = {<\/p>\n
'offset': offset,<\/p>\n
'limit': limit,<\/p>\n
'sort_by': 'default'<\/p>\n
}<\/p>\n
try:<\/p>\n
response = requests.get(url, headers=headers, params=params)<\/p>\n
response.raise_for_status()<\/p>\n
data = response.json()<\/p>\n
except requests.exceptions.RequestException as e:<\/p>\n
print(f"\u8bf7\u6c42\u5931\u8d25\uff1a{e}")<\/p>\n
return None<\/p>\n
return data<\/p>\n
question_id = '1234567890' # \u793a\u4f8b\u95ee\u9898ID<\/p>\n
offset = 0<\/p>\n
limit = 20<\/p>\n
create_table()<\/p>\n
while True:<\/p>\n
data = get_answers(question_id, offset, limit)<\/p>\n
if data is None:<\/p>\n
break<\/p>\n
answers = data['data']<\/p>\n
if not answers:<\/p>\n
break<\/p>\n
for answer in answers:<\/p>\n
insert_answer(answer['content'])<\/p>\n
offset += limit<\/p>\n
<\/code><\/pre>\n<\/p>\n<\/li>\n
\n\u6570\u636e\u5206\u6790<\/strong><\/p>\n\u5728\u83b7\u53d6\u5230\u77e5\u4e4e\u7684\u6570\u636e\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684pandas\u5e93\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u6790\u548c\u5904\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u6570\u636e\u5206\u6790\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\nimport requests<\/p>\n
def get_answers(question_id, offset=0, limit=20):<\/p>\n
url = f'https:\/\/www.zhihu.com\/api\/v4\/questions\/{question_id}\/answers'<\/p>\n
headers = {<\/p>\n
'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36'<\/p>\n
}<\/p>\n
params = {<\/p>\n
'offset': offset,<\/p>\n
'limit': limit,<\/p>\n
'sort_by': 'default'<\/p>\n
}<\/p>\n
try:<\/p>\n
response = requests.get(url, headers=headers, params=params)<\/p>\n
response.raise_for_status()<\/p>\n
data = response.json()<\/p>\n
except requests.exceptions.RequestException as e:<\/p>\n
print(f"\u8bf7\u6c42\u5931\u8d25\uff1a{e}")<\/p>\n
return None<\/p>\n
return data<\/p>\n
question_id = '1234567890' # \u793a\u4f8b\u95ee\u9898ID<\/p>\n
offset = 0<\/p>\n
limit = 20<\/p>\n
all_answers = []<\/p>\n
while True:<\/p>\n
data = get_answers(question_id, offset, limit)<\/p>\n
if data is None:<\/p>\n
break<\/p>\n
answers = data['data']<\/p>\n
if not answers:<\/p>\n
break<\/p>\n
for answer in answers:<\/p>\n
all_answers.append(answer['content'])<\/p>\n
offset += limit<\/p>\n
df = pd.DataFrame(all_answers, columns=['content'])<\/p>\n
print(df.describe())<\/p>\n
<\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u5229\u7528Python\u5faa\u73af\u83b7\u53d6\u77e5\u4e4e\u4e0a\u7684\u6570\u636e\uff0c\u5e76\u5bf9\u6570\u636e\u8fdb\u884c\u5b58\u50a8\u548c\u5206\u6790\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\u3002\u5982\u679c\u4f60\u6709\u4efb\u4f55\u95ee\u9898\u6216\u9700\u8981\u8fdb\u4e00\u6b65\u7684\u5e2e\u52a9\uff0c\u8bf7\u968f\u65f6\u8054\u7cfb\u6211\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n \u5982\u4f55\u4f7f\u7528Python\u5b9e\u73b0\u5bf9\u77e5\u4e4e\u5185\u5bb9\u7684\u5faa\u73af\u8bbf\u95ee\uff1f<\/strong>
\u8981\u4f7f\u7528Python\u5faa\u73af\u8bbf\u95ee\u77e5\u4e4e\u5185\u5bb9\uff0c\u53ef\u4ee5\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u5e93\u5982Requests\u548cBeautifulSoup\u3002\u901a\u8fc7\u6784\u9020URL\u5e76\u53d1\u9001\u8bf7\u6c42\uff0c\u89e3\u6790\u8fd4\u56de\u7684HTML\u5185\u5bb9\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u53ef\u4ee5\u7ed3\u5408\u5faa\u73af\u7ed3\u6784\uff0c\u6301\u7eed\u8bbf\u95ee\u4e0d\u540c\u7684\u9875\u9762\u6216\u5185\u5bb9\uff0c\u5b9e\u73b0\u6570\u636e\u7684\u81ea\u52a8\u6293\u53d6\u3002<\/p>\n\u5728\u5faa\u73af\u8bbf\u95ee\u77e5\u4e4e\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u63aa\u65bd\uff1f<\/strong>
\u77e5\u4e4e\u5bf9\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u6709\u4e00\u5b9a\u7684\u53cd\u722c\u866b\u673a\u5236\uff0c\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406IP\u548c\u9002\u5f53\u5ef6\u8fdf\u8bf7\u6c42\u6765\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u968f\u673a\u7684User-Agent\u4e5f\u80fd\u5e2e\u52a9\u6a21\u62df\u771f\u5b9e\u7528\u6237\u7684\u8bbf\u95ee\u884c\u4e3a\uff0c\u4ece\u800c\u63d0\u9ad8\u722c\u53d6\u7684\u6210\u529f\u7387\u3002<\/p>\n\u4f7f\u7528Python\u6293\u53d6\u77e5\u4e4e\u6570\u636e\u65f6\uff0c\u6709\u54ea\u4e9b\u5e93\u63a8\u8350\uff1f<\/strong>
\u5728\u6293\u53d6\u77e5\u4e4e\u6570\u636e\u65f6\uff0c\u63a8\u8350\u4f7f\u7528Requests\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42\uff0cBeautifulSoup\u6216lxml\u8fdb\u884cHTML\u89e3\u6790\uff0cPandas\u7528\u4e8e\u6570\u636e\u5904\u7406\u548c\u5b58\u50a8\u3002\u6b64\u5916\uff0cScrapy\u6846\u67b6\u4e5f\u5f88\u9002\u5408\u8fdb\u884c\u5927\u89c4\u6a21\u7684\u6570\u636e\u6293\u53d6\uff0c\u80fd\u591f\u7b80\u5316\u5904\u7406\u6d41\u7a0b\uff0c\u63d0\u9ad8\u6548\u7387\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u77e5\u4e4e\u7684API\u548c\u5faa\u73af\u7ed3\u6784\u6765\u5b9e\u73b0\u5faa\u73af\u4e00\u6b21\u77e5\u4e4e\u7684\u64cd\u4f5c\u3002 \u5229\u7528\u77e5\u4e4eAPI\u3001\u4f7f\u7528reque […]","protected":false},"author":3,"featured_media":1050570,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1050563"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1050563"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1050563\/revisions"}],"predecessor-version":[{"id":1050573,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1050563\/revisions\/1050573"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1050570"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1050563"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1050563"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1050563"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"python\u5982\u4f55\u5faa\u73af\u4e00\u6b21\u77e5\u4e4e\"](\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/bfd1816f-7ab2-4415-8246-bcf817162115.webp?x-oss-process=image\/auto-orient,1\/format,webp\")
<\/p>\n