# \u4efb\u52a11\u8bf4\u660e\u6587\u6863<\/p>\n
\u9879\u76ee\u73af\u5883\uff1a
\n```python
\njupyter 4.5.0
\nPython 3.7.4
\nbs4
\nrequests
\n```
\n\u4f7f\u7528\u7ad9\u70b9\uff1a
\n```html
\nhttps:\/\/www.scrapethissite.com\/pages\/forms\/
\n```<\/p>\n
## 1\u3001\u4f9d\u8d56\u73af\u5883\u5b89\u88c5<\/p>\n
pip\u5b89\u88c5requests\u548cbs4\u5e93
\n```cmd
\npip install requests beautifulsoup4
\n```
\n\u5176\u4e2d\uff0c
\n* requests\u7528\u4e8e\u53d1\u9001\u7f51\u9875\u8bf7\u6c42\u548c\u83b7\u53d6\u7f51\u9875\u6e90\u4ee3\u7801\u3002
\n* BeautifulSoup\u7528\u4e8e\u89e3\u6790html\u4ee3\u7801\u4ee5\u63d0\u53d6\u6570\u636e\u3002<\/p>\n
## 2\u3001\u5b9a\u4e49\u7f51\u7ad9\u57fa\u7840URL<\/p>\n
\u6211\u4eec\u53c2\u8003\u7f51\u5740\uff0c\u89c2\u5bdf\u53ef\u5f97
\n```Python
\nurl = \"https:\/\/www.scrapethissite.com\/pages\/forms\/\"
\n```<\/p>\n
## 3\u3001\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u6e90\u7801<\/p>\n
\u4e3a\u4e86\u65b9\u4fbf\uff0c\u6211\u4eec\u5229\u7528Python\u5185\u7f6e\u7684`html.parser`\u89e3\u6790\u5668\uff0c\u89e3\u6790hteml\u6e90\u7801\u3002
\n```Python
\nsoup = BeautifulSoup(html_content,\"html.parser\")
\n```
\n## 4\u3001\u5b9a\u4f4d\u6240\u6709\u7403\u961f\u7684\u6570\u636e\u8282\u70b9<\/p>\n
\u6211\u4eec\u901a\u8fc7\u89c2\u5bdf\u7f51\u9875\u6e90\u7801\uff0c\u53d1\u73b0\u50a8\u5b58\u7403\u961f\u6570\u636e\u7684\u4f4d\u7f6e
\n\u4e0d\u96be\u53d1\u73b0\uff0c\u6bcf\u4e2atr\u6807\u7b7e\u5bf9\u5e94\u4e00\u53ea\u7403\u961f\u7684\u5b8c\u6574\u6570\u636e\u3002
\n```Python
\nteams = soup.find_all(\"tr\",class_=\"team\")
\n```
\n## 5\u3001\u904d\u5386\u63d0\u53d6\u7403\u961f\u5b57\u6bb5<\/p>\n
\u540c\u6837\u901a\u8fc7\u89c2\u5bdf\u7f51\u9875\u6e90\u7801\uff0c\u6211\u4eec\u627e\u5230\u6bcf\u4e00\u4e2a\u6211\u4eec\u9700\u8981\u7684\u6570\u636e\u6240\u5bf9\u5e94\u7684\u6807\u7b7e
\n\u4f8b\u5982\uff1a\u961f\u4f0d\u540d\u79f0
\n```Python
\nteam_name = team.find(\"td\",class_=\"name\").text.strip()
\n```
\n\u5176\u4e2d\uff0c
\n* `.text`\u7528\u4e8e\u63d0\u53d6\u6807\u7b7e\u5185\u7684\u672c\u6587
\n* `.strip()`\u7528\u4e8e\u53bb\u9664\u6587\u672c\u524d\u540e\u7684\u7a7a\u683c\u548c\u6362\u884c\u7b26<\/p>\n
\u503c\u5f97\u6ce8\u610f\u7684\u662f\uff0c\u6709\u4e00\u4e9b\u6570\u636e\u6709\u4e24\u79cd\u4e0d\u540c\u7684\u6807\u7b7e\u3002<\/mark>\u6bd4\u5982\u6211\u4eec\u767e\u5206\u6bd4\u80dc\u7387\u53ef\u80fd\u662f`text-success`\u6216\u8005`text-danger`\u3002\u5982\u679c\u6211\u4eec\u4e0d\u505a\u8c03\u6574\uff0c\u4f1a\u62a5\u63d0\u53d6\u7a7a\u6570\u636e\u7684\u9519\u8bef\u3002 ## 6\u3001\u50a8\u5b58\u6570\u636e\u548c\u6253\u5370\u8fdb\u5ea6<\/p>\n \u4e3a\u9002\u914dcsv\u6211\u4eec\u628a\u5b57\u7b26\u7528**\u9017\u53f7\u5206\u9694** \u4fdd\u5b58\u6570\u636e ## 7\u3001\u7ffb\u9875\u722c\u53d6\u529f\u80fd<\/p>\n #### 7.1\u3001\u7ffb\u9875url<\/p>\n \u89c2\u5bdf\u7f51\u5740\u5f97\u5230\u7ffb\u9875\u7684url\u4e3a:<\/p>\n `\u539f\u7f51\u5740?page=\u9875\u7801` #### 7.2\u3001\u904d\u5386\u961f\u4f0d<\/p>\n \u4e0e\u7b2c\u4e00\u9875\u4ee3\u7801\u5b8c\u5168\u4e00\u81f4\uff0c\u6545\u4e0d\u4f5c\u8d58\u8ff0\u3002<\/p>\n #### 7.3\u3001\u81ea\u52a8\u547d\u540d\u6587\u4ef6<\/p>\n ```Python ## 8\u3001\u641c\u7d22\u722c\u53d6\u529f\u80fd<\/p>\n #### 8.1\u3001\u5b9a\u4e49\u5f85\u641c\u7d22\u7403\u961f\u540d\u5355<\/p>\n \u6211\u4eec\u8981\u5236\u4f5c\u4e00\u4e2a\u5f85\u641c\u7d22\u540d\u5355\uff0c\u5305\u542b\uff1a #### 8.2\u3001\u6784\u9020\u641c\u7d22\u7528url<\/p>\n \u89c2\u5bdf\u7f51\u9875\u5f97\u5230url\u641c\u7d22\u53c2\u6570 #### 8.3\u3001\u904d\u5386 ## \u4e0b\u9762\u662f\u5168\u90e8\u4ee3\u78011 url = \"https:\/\/www.scrapethissite.com\/pages\/forms\/\"<\/p>\n # \u4fdd\u7559\u4f60\u539f\u6709\u7684\u7b2c1\u9875\u722c\u53d6\u4ee3\u7801 soup = BeautifulSoup(html_content, \"html.parser\") <\/p>\n teams = soup.find_all(\"tr\", class_=\"team\")<\/p>\n lines = [] print(f\"\u63d0\u53d6\u5b8c\u6210\uff0c\u5171 {len(teams)} \u4e2a\u961f\u4f0d\")<\/p>\n with open('hockey_teams_page_1.csv', 'w') as f: # \u65b0\u589e\u7ffb\u9875\u722c\u53d6\u7b2c2-5\u9875\u7684\u4ee3\u7801 soup = BeautifulSoup(html_content, \"html.parser\") <\/p>\n teams = soup.find_all(\"tr\", class_=\"team\")<\/p>\n lines = [] print(f\"\u7b2c{page_num}\u9875\u63d0\u53d6\u5b8c\u6210\uff0c\u5171 {len(teams)} \u4e2a\u961f\u4f0d\")<\/p>\n # \u4fdd\u5b58\u4e3a\u5bf9\u5e94\u9875\u7801\u7684CSV\u6587\u4ef6 #\u65b0\u589e\u641c\u7d22\u722c\u53d6 for team_name, file_suffix in teams_to_search: soup = BeautifulSoup(html_content, \"html.parser\") <\/p>\n teams = soup.find_all(\"tr\", class_=\"team\")<\/p>\n lines = [] print(f\"{team_name}\u63d0\u53d6\u5b8c\u6210\uff0c\u5171 {len(teams)} \u4e2a\u961f\u4f0d\")<\/p>\n # \u4fdd\u5b58\u4e3a\u6307\u5b9a\u6587\u4ef6\u540d # \u4efb\u52a12\u8bf4\u660e\u6587\u6863<\/p>\n \u9879\u76ee\u73af\u5883\uff1a ## 1\u3001\u5206\u6790\u9875\u9762\u548c\u63a5\u53e3<\/p>\n \u6211\u4eec\u8981\u722c\u53d6\u7684\u662f**\u7eafjson\u683c\u5f0f\u63a5\u53e3\u6570\u636e**\uff0c\u65e0\u524d\u7aef\u9875\u9762\u6e32\u67d3\uff0c\u5c5e\u4e8e**ajax\u5f02\u6b65\u6570\u636e\u63a5\u53e3** ## 2\u3001\u8bf7\u6c42\u65b9\u5f0f<\/p>\n #### 2.1\u3001\u8bf7\u6c42\u7c7b\u578b\u548c\u53c2\u6570<\/p>\n \u6211\u4eec\u4f7f\u7528*GET*\u8bf7\u6c42\u8bf7\u6c42`userId`\u7528\u6237\u7684\u5e16\u5b50\u6570\u636e<\/p>\n #### 2.2\u3001\u914d\u7f6e\u8bf7\u6c42\u5934 ## 3\u3001\u6570\u636e\u5904\u7406<\/p>\n #### 3.1\u3001\u6570\u636e\u89e3\u6790 #### 3.2\u3001\u904d\u5386\u5e76\u63d0\u53d6\u5b57\u6bb5 ## 4\u3001\u4fdd\u5b58\u6570\u636e<\/p>\n 1. \u5148\u521b\u5efa\u6587\u4ef6\u5939`os.makedirs`\u521b\u5efa`user_posts`\u6587\u4ef6\u5939\u7528\u4e8e\u4fdd\u5b58csv\u6587\u4ef6 ## \u4e0b\u9762\u662f\u5168\u90e8\u4ee3\u78012 def scrape(user_id: int): # 2. \u53d1\u9001\u8bf7\u6c42 response = requests.get(base_url, params=params, headers=headers)<\/p>\n # 3. \u76f4\u63a5\u89e3\u6790 JSON \u6570\u636e # 4. \u63d0\u53d6\u6570\u636e # 5. \u4fdd\u5b58\u6587\u4ef6 # \u5faa\u73af\u722c\u53d6\u591a\u4e2a\u7528\u6237+ \u4f11\u7720\u9632\u5c01 # \u4efb\u52a11\u8bf4\u660e\u6587\u6863 \u9879\u76ee\u73af\u5883\uff1a “`python jupyter 4.5.0 Python 3.7.4 bs4 requests …<\/p>\n","protected":false},"author":1,"featured_media":117,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","emotion":"","emotion_color":"","title_style":"","license":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-104","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/posts\/104","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=104"}],"version-history":[{"count":12,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/posts\/104\/revisions"}],"predecessor-version":[{"id":116,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/posts\/104\/revisions\/116"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=\/wp\/v2\/media\/117"}],"wp:attachment":[{"href":"https:\/\/www.becksai.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=104"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=104"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.becksai.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=104"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\u56e0\u6b64**\u6211\u4eec\u8981\u901a\u8fc7\u903b\u8f91\u5224\u65ad\u6765\u9009\u62e9\u6027\u63d0\u53d6\u975e\u7a7a\u7684\u6570\u636e**\uff1a
\n```Python
\nwin_td = team.select_one(\"td.pct.text-success, td.pct.text-danger\")
\nwin_pct = win_td.text.strip() if win_td else \"\"
\n```<\/p>\n
\n\u6211\u4eec\u628a\u6570\u636e\u4fdd\u5b58\u5728`lines`\u4e2d
\n\u6253\u5370\u8fdb\u5ea6
\n```Python
\nline = f\"{TeamName},{Year},{Wins},{Losses},{OTLosses},{win_pct},{GoalsFor},{GoalsAgainst},{diff}\\n\"
\nprint(f\"\u5df2\u63d0\u53d6\u961f\u4f0d\uff1a{TeamName}\")
\nlines.append(line)
\n```<\/p>\n
\n```Python
\nwith open('hockey_teams_page_1.csv', 'w') as f:
\n f.write(\"TeamName,Year,Wins,Losses,OTLosses,Win%,GoalsFor(GF),GoalsAgainst(GA),+\/-\\n\")
\n f.writelines(lines)
\n```<\/p>\n
\n\u56e0\u6b64\u6784\u9020\u7ffb\u9875url\u4e3a
\n```Python
\npage_url = f\"{url}?page={page_num}\"
\n```
\n\u5f53\u7136\u6211\u4eec\u9700\u8981\u904d\u5386\u4e00\u4e0b\u9875\u7801\uff0c\u4e0d\u4f5c\u8d58\u8ff0\u3002<\/p>\n
\nfilename = f\"hockey_teams_page_{page_num}.csv\"
\n```
\n\u5f53\u7136\u4f60\u4e5f\u53ef\u4ee5**\u679a\u4e3e**\u5b9e\u73b0\u7c7b\u4f3c\u7684\u6548\u679c\u3002<\/p>\n
\n* \u4e2d\u6587\u663e\u793a\u540d(\u7528\u4e8e\u641c\u7d22)
\n* \u6587\u4ef6\u4fdd\u5b58\u540e\u7f00(\u7528\u4e8e\u533a\u5206\u6587\u4ef6)
\n```Python
\nteams_to_search = [
\n (\"Boston Bruins\", \"boston_bruins\"),
\n (\"Buffalo Sabres\", \"buffalo_sabres\")
\n]
\n```<\/p>\n
\n`\u539f\u7f51\u5740?q=\u952e\u5165\u6570\u636e\uff08\u7403\u961f\u540d\u79f0\uff09`
\n\u6211\u4eec\u8fd8\u9700\u8981\u5c06\u7403\u961f\u540d\u79f0\u4e2d\u7684\u7a7a\u683c\u66ff\u6362\u4e3a +\uff08URL \u53c2\u6570\u683c\u5f0f\u8981\u6c42\uff09<\/mark>\uff0c\u62fc\u63a5\u641c\u7d22\u53c2\u6570\uff1a
\n```Python
\nsearch_url = f\"{url}?q={team_name.replace(' ', '+')}\"
\n```
\n*\u9898\u5916\u8bdd\uff0c\u4f60\u7528\u641c\u7d22\u5f15\u64ce\u7684\u65f6\u5019\u4e5f\u53ef\u4ee5\u4f7f\u7528\u8fd9\u4e2a\u683c\u5f0f\u4f5c\u4e3a\u641c\u7d22\u5173\u952e\u8bcd\u7684\u6280\u5de7\u3002\uff1aD*<\/p>\n
\n\u6211\u4eec\u53ea\u9700\u8981\u66f4\u6539\u8bf7\u6c42\u7684\u641c\u7d22\u9875\u4e3a\u6211\u4eec\u7684`search_url`\uff0c\u4ee5\u53caprint\u548c\u4fdd\u5b58\u7684csv\u6587\u4ef6\u540d\u3002<\/p>\n
\n```Python
\nimport requests
\nfrom bs4 import BeautifulSoup<\/p>\n
\nresponse = requests.get(url)
\nhtml_content = response.text<\/p>\n
\nfor team in teams:
\n TeamName = team.find(\"td\", class_=\"name\").text.strip()
\n Year = team.find(\"td\", class_=\"year\").text.strip()
\n Wins = team.find(\"td\", class_=\"wins\").text.strip()
\n Losses = team.find(\"td\", class_=\"losses\").text.strip()
\n OTLosses = team.find(\"td\", class_=\"ot-losses\").text.strip()
\n win_td = team.select_one(\"td.pct.text-success, td.pct.text-danger\")
\n win_pct = win_td.text.strip() if win_td else \"\"
\n GoalsFor = team.find(\"td\", class_=\"gf\").text.strip()
\n GoalsAgainst = team.find(\"td\", class_=\"ga\").text.strip()
\n diff_td = team.select_one(\"td.diff.text-success, td.diff.text-danger\")
\n diff = diff_td.text.strip() if diff_td else \"\"
\n line = f\"{TeamName},{Year},{Wins},{Losses},{OTLosses},{win_pct},{GoalsFor},{GoalsAgainst},{diff}\\n\"
\n print(f\"\u5df2\u63d0\u53d6\u961f\u4f0d\uff1a{TeamName}\")
\n lines.append(line)<\/p>\n
\n f.write(\"TeamName,Year,Wins,Losses,OTLosses,Win%,GoalsFor(GF),GoalsAgainst(GA),+\/-\\n\")
\n f.writelines(lines)<\/p>\n
\nfor page_num in range(2, 6):
\n # \u6784\u9020\u5f53\u524d\u9875URL
\n page_url = f\"{url}?page={page_num}\"
\n response = requests.get(page_url)
\n html_content = response.text<\/p>\n
\n for team in teams:
\n TeamName = team.find(\"td\", class_=\"name\").text.strip()
\n Year = team.find(\"td\", class_=\"year\").text.strip()
\n Wins = team.find(\"td\", class_=\"wins\").text.strip()
\n Losses = team.find(\"td\", class_=\"losses\").text.strip()
\n OTLosses = team.find(\"td\", class_=\"ot-losses\").text.strip()
\n win_td = team.select_one(\"td.pct.text-success, td.pct.text-danger\")
\n win_pct = win_td.text.strip() if win_td else \"\"
\n GoalsFor = team.find(\"td\", class_=\"gf\").text.strip()
\n GoalsAgainst = team.find(\"td\", class_=\"ga\").text.strip()
\n diff_td = team.select_one(\"td.diff.text-success, td.diff.text-danger\")
\n diff = diff_td.text.strip() if diff_td else \"\"
\n line = f\"{TeamName},{Year},{Wins},{Losses},{OTLosses},{win_pct},{GoalsFor},{GoalsAgainst},{diff}\\n\"
\n print(f\"\u5df2\u63d0\u53d6\u7b2c{page_num}\u9875\u961f\u4f0d\uff1a{TeamName}\")
\n lines.append(line)<\/p>\n
\n filename = f\"hockey_teams_page_{page_num}.csv\"
\n with open(filename, 'w') as f:
\n f.write(\"TeamName,Year,Wins,Losses,OTLosses,Win%,GoalsFor(GF),GoalsAgainst(GA),+\/-\\n\")
\n f.writelines(lines)<\/p>\n
\nteams_to_search = [
\n (\"Boston Bruins\", \"boston_bruins\"),
\n (\"Buffalo Sabres\", \"buffalo_sabres\")
\n]<\/p>\n
\n # \u6784\u9020\u641c\u7d22URL\uff08\u5c06\u7a7a\u683c\u66ff\u6362\u4e3a+\uff0c\u7b26\u5408URL\u53c2\u6570\u683c\u5f0f\uff09
\n search_url = f\"{url}?q={team_name.replace(' ', '+')}\"
\n response = requests.get(search_url)
\n html_content = response.text<\/p>\n
\n for team in teams:
\n TeamName = team.find(\"td\", class_=\"name\").text.strip()
\n Year = team.find(\"td\", class_=\"year\").text.strip()
\n Wins = team.find(\"td\", class_=\"wins\").text.strip()
\n Losses = team.find(\"td\", class_=\"losses\").text.strip()
\n OTLosses = team.find(\"td\", class_=\"ot-losses\").text.strip()
\n win_td = team.select_one(\"td.pct.text-success, td.pct.text-danger\")
\n win_pct = win_td.text.strip() if win_td else \"\"
\n GoalsFor = team.find(\"td\", class_=\"gf\").text.strip()
\n GoalsAgainst = team.find(\"td\", class_=\"ga\").text.strip()
\n diff_td = team.select_one(\"td.diff.text-success, td.diff.text-danger\")
\n diff = diff_td.text.strip() if diff_td else \"\"
\n line = f\"{TeamName},{Year},{Wins},{Losses},{OTLosses},{win_pct},{GoalsFor},{GoalsAgainst},{diff}\\n\"
\n print(f\"\u5df2\u63d0\u53d6{team_name}\u961f\u4f0d\uff1a{TeamName}\")
\n lines.append(line)<\/p>\n
\n filename = f\"hockey_teams_{file_suffix}.csv\"
\n with open(filename, 'w') as f:
\n f.write(\"TeamName,Year,Wins,Losses,OTLosses,Win%,GoalsFor(GF),GoalsAgainst(GA),+\/-\\n\")
\n f.writelines(lines)
\n```<\/p>\n
\n```python
\njupyter 4.5.0
\nPython 3.7.4
\nrequests
\n```
\n\u4f7f\u7528\u7ad9\u70b9\uff1a
\n```html
\nhttps:\/\/jsonplaceholder.typicode.com\/posts
\n```
\n\u5df2\u5b89\u88c5\u8fc7*requests*\uff0c\u4e0d\u518d\u505a\u8d58\u8ff0\u3002<\/p>\n
\n\u6211\u4eec\u901a\u8fc7*userId*\u53c2\u6570\u7b5b\u9009**\u6307\u5b9a\u7528\u6237\u7684\u6240\u6709\u5e16\u5b50**\uff0c\u5e76\u8fd4\u56de`id`,`title`,`body`,`userId`\u7684\u6570\u7ec4<\/p>\n
\n```Python
\nheaders = {
\n \"User-Agent\": \"\u6d4f\u89c8\u5668\u6807\u8bc6\",
\n \"X-Requested-With\": \"XMLHttpRequest\" # \u6807\u8bb0\u4e3aAJAX\u8bf7\u6c42
\n}
\n```<\/p>\n
\n\u76f4\u63a5\u7528`response.json()`**\u5c06\u63a5\u53e3\u8fd4\u56de\u7684json\u5b57\u7b26\u4e32\u8f6c\u4e3aPython\u7684\u5217\u8868\u3002**<\/p>\n
\n\u904d\u5386\u5b57\u6bb5\u63d0\u53d6:
\n* \u5e16\u5b50id\uff1a`post_id`
\n* \u5e16\u5b50\u6807\u9898:`title`
\n* \u5e16\u5b50\u6b63\u6587\u5185\u5bb9\uff1a`content`
\n\u5e76\u7528\",\"\u62fc\u63a5\u4e3acsv<\/p>\n
\n2. \u6309\u7528\u6237id\u547d\u540d\uff0c\u5199\u5165\u8868\u5934\u5e76\u6279\u91cf\u5199\u5165\u6570\u636e
\n\u6ce8\u610f\uff1a\u7f16\u7801\u683c\u5f0f\u4f7f\u7528UTF-8<\/mark>
\n3. \u5229\u7528`time.sleep(1)`**\u63a7\u5236\u722c\u53d6\u9891\u7387**<\/p>\n
\n```Python
\nimport os
\nimport requests
\nimport time<\/p>\n
\n # 1. \u76ee\u6807\u63a5\u53e3 URL
\n # \u901a\u8fc7\u6539\u53d8 user_id \u53c2\u6570\u83b7\u53d6\u4e0d\u540c\u7528\u6237\u7684\u53d1\u5e16\u6570\u636e
\n base_url = \"https:\/\/jsonplaceholder.typicode.com\/posts\"
\n params = {
\n \"userId\": user_id # \u6309\u7528\u6237ID\u7b5b\u9009\u5e16\u5b50
\n }<\/p>\n
\n headers = {
\n \"User-Agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36\",
\n \"X-Requested-With\": \"XMLHttpRequest\"
\n }<\/p>\n
\n data = response.json()<\/p>\n
\n lines = []
\n for post in data:
\n post_id = post.get(\"id\")
\n title = post.get(\"title\")
\n content = post.get(\"body\")
\n # \u62fc\u63a5\u884c
\n line = f\"{post_id},{title},{content}\\n\"
\n lines.append(line)<\/p>\n
\n os.makedirs('user_posts', exist_ok=True)
\n with open(f'user_posts\/{user_id}.csv', 'w', encoding='utf-8') as f:
\n f.write(\"post_id,title,content\\n\") # \u8868\u5934
\n f.writelines(lines)
\n print(f\"\u6210\u529f\u63d0\u53d6\u7528\u6237{user_id}\u7684\u53d1\u5e16\u6570\u636e\")<\/p>\n
\nfor user_id in [1, 2, 3, 4, 5]:
\n scrape(user_id)
\n time.sleep(1)
\n```<\/p>\n","protected":false},"excerpt":{"rendered":"