बड़े डेटासेट का पृष्ठांकन और संग्रह

all_items = []
next_url = "https://api.example.com/items?limit=100"
while next_url:
    resp = requests.get(next_url, timeout=10)
    resp.raise_for_status()
    data = resp.json()
    all_items.extend(data["results"])
    next_url = data.get("next")   # None when no more pages
print(len(all_items))

import time

while next_url:
    resp = requests.get(next_url, timeout=10)
    resp.raise_for_status()
    data = resp.json()
    all_items.extend(data["results"])
    next_url = data.get("next")
    time.sleep(0.5)   # 2 requests per second

remaining = int(resp.headers.get("X-RateLimit-Remaining", 1))
if remaining < 5:
    reset = int(resp.headers.get("X-RateLimit-Reset", 1))
    print("Near limit, sleeping", reset, "s")
    time.sleep(reset)

resp = requests.get(url, timeout=10)
if resp.status_code == 429:
    wait = int(resp.headers.get("Retry-After", 5))
    time.sleep(wait)
    resp = requests.get(url, timeout=10)   # retry once

from tqdm import tqdm

for page in tqdm(range(1, 101), desc="Fetching"):
    resp = requests.get(url, params={"page": page}, timeout=10)
    all_items.extend(resp.json())
    time.sleep(0.2)

from tqdm import tqdm

pbar = tqdm(desc="Pages")
while next_url:
    resp = requests.get(next_url, timeout=10)
    data = resp.json()
    all_items.extend(data["results"])
    next_url = data.get("next")
    pbar.update(1)
pbar.close()

import json

with open("items.jsonl", "w") as f:
    while next_url:
        resp = requests.get(next_url, timeout=10)
        data = resp.json()
        for item in data["results"]:
            f.write(json.dumps(item) + "\n")
        next_url = data.get("next")

import os

start_page = 1
if os.path.exists("checkpoint.txt"):
    start_page = int(open("checkpoint.txt").read()) + 1

for page in range(start_page, 1000):
    # ... fetch and store ...
    open("checkpoint.txt", "w").write(str(page))

from tqdm import tqdm
import time, json

with open("out.jsonl", "a") as f:
    next_url = "https://api.example.com/items?limit=100"
    pbar = tqdm(desc="Pages")
    while next_url:
        r = requests.get(next_url, timeout=10)
        r.raise_for_status()
        d = r.json()
        for it in d["results"]:
            f.write(json.dumps(it) + "\n")
        next_url = d.get("next")
        pbar.update(1)
        time.sleep(0.3)