BOSS Zhipin: 3 skills for AI agents

def click_filter(label_text):
    """Click a filter tab by its text label."""
    js(f"""
    (function() {{
        var labels = document.querySelectorAll('.chat-user .label-list li .label-name');
        for (var i = 0; i < labels.length; i++) {{
            if (labels[i].textContent.trim().indexOf('{label_text}') === 0) {{
                labels[i].closest('li').click();
                return true;
            }}
        }}
        return false;
    }})()
    """)
    wait(1)
 
def click_more_filter(label_text):
    """Click an option inside the '更多' dropdown."""
    # First open the dropdown
    click_filter("更多")
    wait(0.5)
    js(f"""
    (function() {{
        var items = document.querySelectorAll('.more-label li span');
        for (var i = 0; i < items.length; i++) {{
            if (items[i].textContent.trim() === '{label_text}') {{
                items[i].closest('li').click();
                return true;
            }}
        }}
        return false;
    }})()
    """)
    wait(1)

def get_conversations():
    raw = js("""
    (function() {
        var items = document.querySelectorAll('.friend-content');
        var results = [];
        for (var i = 0; i < items.length; i++) {
            var el = items[i];
            var text = el.textContent;
            var badge = el.querySelector('[class*="badge"], [class*="unread"], [class*="count"]');
            var unread = badge ? parseInt(badge.textContent) || 0 : 0;
            results.push({
                text: text.trim().substring(0, 150),
                is_top: el.classList.contains('friend-top'),
                unread: unread
            });
        }
        return JSON.stringify(results);
    })()
    """)
    return json.loads(raw)

def open_conversation(index=0):
    js(f"document.querySelectorAll('.friend-content')[{index}].click()")
    wait(2)

{
    "mid": 337069469603329,              # message ID (numeric, for pagination)
    "type": 3,                           # 3=regular message, 4=system message
    "received": true,                    # whether you received it
    "body": {
        "type": 1,                       # 1=text, 8=job card
        "text": "message text here...",  # present when body.type=1
        "jobDesc": { ... }               # present when body.type=8
    },
    "from": {
        "uid": 502838021,                # sender user ID
        "name": "张女士",
        "avatar": "https://img.bosszhipin.com/..."
    },
    "to": {
        "uid": 680839465                 # recipient user ID
    }
}

{
    "body": {
        "type": 8,
        "headTitle": "您正在与Boss刘女士直接沟通如下职位",
        "jobDesc": {
            "title": "AI Agent工程师",
            "salary": "35-60K·16薪",         # REAL salary — not font-encoded
            "company": "Soul App",
            "city": "上海 浦东新区 金桥",
            "experience": "经验不限",
            "education": "硕士",
            "stage": "D轮及以上",
            "positionCategory": "算法工程师",
            "boss": {
                "uid": 3872648,
                "name": "刘女士",
                "avatar": "https://img.bosszhipin.com/..."
            },
            "bossTitle": "招聘专家",
            "jobId": 509933581
        }
    }
}

def fetch_messages(boss_id, page=1, count=20):
    raw = js(f"""
    (async function() {{
        var url = '/wapi/zpchat/geek/historyMsg?bossId={boss_id}&maxMsgId=0&c={count}&page={page}&src=0';
        var r = await fetch(url);
        var d = await r.json();
        if (d.code !== 0 || !d.zpData) {{
            return JSON.stringify({{code: d.code, hasMore: false, count: 0, messages: [], error: d.msg || 'API error'}});
        }}
        var msgs = d.zpData.messages || [];
        return JSON.stringify({{
            code: d.code,
            hasMore: d.zpData.hasMore,
            count: msgs.length,
            messages: msgs.map(function(m) {{
                var b = m.body || {{}};
                return {{
                    mid: m.mid,
                    type: m.type,
                    body_type: b.type,
                    text: b.text || null,
                    job: b.jobDesc ? {{
                        title: b.jobDesc.title,
                        salary: b.jobDesc.salary,
                        company: b.jobDesc.company,
                        city: b.jobDesc.city,
                        boss_name: (b.jobDesc.boss || {{}}).name,
                        job_id: b.jobDesc.jobId
                    }} : null,
                    from_name: (m.from || {{}}).name,
                    from_uid: (m.from || {{}}).uid,
                    received: m.received
                }};
            }})
        }});
    }})()
    """)
    return json.loads(raw)

def fetch_all_messages(boss_id):
    all_msgs = []
    max_msg_id = 0
    while True:
        raw = js(f"""
        (async function() {{
            var r = await fetch('/wapi/zpchat/geek/historyMsg?bossId={boss_id}&maxMsgId={max_msg_id}&c=20&page=1&src=0');
            var d = await r.json();
            if (d.code !== 0 || !d.zpData) {{
                return JSON.stringify({{messages: [], hasMore: false}});
            }}
            return JSON.stringify(d.zpData);
        }})()
        """)
        data = json.loads(raw)
        msgs = data.get("messages", [])
        if not msgs:
            break
        all_msgs.extend(msgs)
        if not data.get("hasMore"):
            break
        max_msg_id = msgs[-1]["mid"]  # smallest mid
        wait(0.5)
    return all_msgs

def read_messages_dom():
    raw = js("""
    (function() {
        var items = document.querySelectorAll('.message-item');
        var results = [];
        for (var i = 0; i < items.length; i++) {
            var el = items[i];
            var timeEl = el.querySelector('.time');
            var textEl = el.querySelector('.text');
            var statusEl = el.querySelector('.message-status');
            results.push({
                from_me: el.classList.contains('item-myself'),
                time: timeEl ? timeEl.textContent.trim() : '',
                text: textEl ? textEl.textContent.trim().substring(0, 300) : '',
                status: statusEl ? statusEl.textContent.trim() : ''
            });
        }
        return JSON.stringify(results);
    })()
    """)
    return json.loads(raw)

def get_current_boss_id():
    return js("""
    (function() {
        var entries = performance.getEntriesByType('resource');
        for (var i = entries.length - 1; i >= 0; i--) {
            var url = entries[i].name;
            if (url.indexOf('/wapi/zpchat/geek/historyMsg') === -1) continue;
            var match = url.match(/bossId=([^&]+)/);
            if (match) return match[1];
        }
        return null;
    })()
    """)

import json
 
goto_url("https://www.zhipin.com/web/geek/jobs?ka=open_joblist")
wait_for_load()
wait(3)
 
jobs = json.loads(js("""
(async function() {
    var r = await fetch('/wapi/zpgeek/pc/recommend/job/list.json?page=1&pageSize=15&city=101020100');
    var d = await r.json();
    if (d.code !== 0 || !d.zpData) { return JSON.stringify([]); }
    return JSON.stringify(d.zpData.jobList || []);
})()
"""))
 
for j in jobs:
    print(j["salaryDesc"], j["jobName"], "|", j["brandName"])

{
    "securityId": "nbyXZvE4kfp6Y...",     # opaque ID for detail API
    "encryptJobId": "cbcbfca3...",          # job detail page ID
    "encryptBossId": "37a64419...",         # recruiter ID
    "jobName": "Aone/GitHub开发工程师",
    "salaryDesc": "18-22K",                 # REAL salary — not font-encoded
    "jobLabels": ["3-5年", "本科", "Java", "Golang"],
    "skills": ["Java", "Golang", "Aone", "GitLab"],
    "jobExperience": "3-5年",
    "jobDegree": "本科",
    "cityName": "上海",
    "areaDistrict": "浦东新区",
    "businessDistrict": "张江",
    "brandName": "软通动力",
    "brandIndustry": "计算机软件",
    "brandScaleName": "10000人以上",
    "brandStageName": "未融资",
    "bossName": "杨女士",
    "bossTitle": "人事",
    "bossOnline": false,
    "bossAvatar": "https://img.bosszhipin.com/...",
    "brandLogo": "https://img.bosszhipin.com/...",
    "welfareList": [],
    "gps": {"longitude": 121.609707, "latitude": 31.185578}
}

import json
 
def fetch_job_list(page=1, page_size=15, city="101020100", **filters):
    """Fetch jobs from the BOSS直聘 API. Must be on a zhipin.com page first."""
    # Default params (matching what the real page sends)
    defaults = {
        "encryptExpectId": "",
        "mixExpectType": "",
        "expectInfo": "",
        "jobType": "",
        "salary": "",
        "experience": "",
        "degree": "",
        "industry": "",
        "scale": ""
    }
    defaults.update(filters)
    params = f"page={page}&pageSize={page_size}&city={city}"
    for k, v in defaults.items():
        params += f"&{k}={v}"
 
    raw = js(f"""
    (async function() {{
        var r = await fetch('/wapi/zpgeek/pc/recommend/job/list.json?{params}');
        var d = await r.json();
        if (d.code !== 0 || !d.zpData) {{
            return JSON.stringify({{code: d.code, hasMore: false, jobs: [], error: d.msg || 'API error'}});
        }}
        return JSON.stringify({{code: d.code, hasMore: d.zpData.hasMore, jobs: d.zpData.jobList || []}});
    }})()
    """)
    return json.loads(raw)
 
# Usage
result = fetch_job_list(page=1, experience=105)  # 3-5年
print(f"Total: {len(result['jobs'])} jobs, hasMore: {result['hasMore']}")
for j in result["jobs"]:
    print(f"  {j['salaryDesc']:12s} {j['jobName']:30s} {j['brandName']}")

def fetch_all_jobs(city="101020100", max_pages=10):
    all_jobs = []
    for page in range(1, max_pages + 1):
        result = fetch_job_list(page=page, city=city)
        all_jobs.extend(result["jobs"])
        if not result["hasMore"] or len(result["jobs"]) == 0:
            break
        wait(0.5)  # polite delay
    return all_jobs

def fetch_job_detail(security_id):
    raw = js(f"""
    (async function() {{
        var r = await fetch('/wapi/zpgeek/job/detail.json?securityId={security_id}');
        var d = await r.json();
        if (d.code !== 0 || !d.zpData) {{
            return JSON.stringify({{code: d.code, error: d.msg || 'API error'}});
        }}
        var zp = d.zpData;
        var job = zp.jobInfo;
        var boss = zp.bossInfo;
        var brand = zp.brandComInfo;
        return JSON.stringify({{
            code: d.code,
            title: job.jobName,
            salary: job.salaryDesc,
            experience: job.experienceName,
            degree: job.degreeName,
            location: job.locationName,
            address: job.address,
            gps: {{lng: job.longitude, lat: job.latitude}},
            description: job.postDescription,
            skills: job.showSkills,
            boss_name: boss.name,
            boss_title: boss.title,
            boss_avatar: boss.large,
            boss_online: boss.online,
            company_name: brand.brandName,
            company_logo: brand.logo,
            company_industry: brand.industryName,
            company_scale: brand.scaleName,
            company_stage: brand.stageName
        }});
    }})()
    """)
    return json.loads(raw)

def get_filter_conditions():
    raw = js("""
    (async function() {
        var r = await fetch('/wapi/zpgeek/pc/all/filter/conditions.json');
        var d = await r.json();
        if (d.code !== 0 || !d.zpData) { return JSON.stringify({}); }
        return JSON.stringify(d.zpData);
    })()
    """)
    return json.loads(raw)
 
# Returns: {
#   experienceList: [{code: 105, name: "3-5年"}, ...],
#   salaryList:     [{code: 406, name: "20-50K", lowSalary: 20, highSalary: 50}, ...],
#   degreeList:     [{code: 203, name: "本科"}, ...],
#   scaleList:      [{code: 305, name: "1000-9999人"}, ...],
#   stageList:      [{code: 807, name: "已上市"}, ...],
#   industryList:   [...],
#   payTypeList:    [...],
#   partTimeList:   [...]
# }

def extract_job_cards_dom():
    raw = js("""
    (function() {
        var cards = document.querySelectorAll('.job-card-box');
        var results = [];
        for (var i = 0; i < cards.length; i++) {
            var card = cards[i];
            function getText(sel) {
                var el = card.querySelector(sel);
                return el ? el.textContent.trim() : '';
            }
            function getHref(sel) {
                var el = card.querySelector(sel);
                return el ? el.href : '';
            }
            var tags = [];
            var tagEls = card.querySelectorAll('.tag-list li');
            for (var t = 0; t < tagEls.length; t++) {
                tags.push(tagEls[t].textContent.trim());
            }
            results.push({
                title: getText('.job-name'),
                salary_raw: getText('.job-salary'),
                tags: tags,
                company: getText('.boss-name'),
                location: getText('.company-location'),
                job_url: getHref('.job-name'),
                company_url: getHref('.boss-info')
            });
        }
        return JSON.stringify(results);
    })()
    """)
    return json.loads(raw)

"input[placeholder='搜索职位、公司']"