File size: 4,477 Bytes
74475ac 7db09ee 74475ac 4259f95 74475ac 5d719e2 74475ac 4259f95 74475ac 7db09ee 74475ac d705151 4259f95 74475ac cc76656 74475ac d705151 4259f95 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
"""Module to crawl the website 'https://www.safe.gov.cn' to fetch and process articles."""
import time
import urllib.request
from datetime import datetime, timedelta
import random
from lxml import etree
from prefect import task, get_run_logger
from controllers.utils import crawl_by_url
@task(name = "Data Collection - safe", log_prints = True)
def crawl(delta):
"""
Crawls the website "https://www.safe.gov.cn" to retrieve policy interpretation and data interpretation articles.
Args:
delta (int): The number of days in the past to consider for crawling.
Returns:
None
"""
logger = get_run_logger()
logger.info("safe.gov.cn")
i = 1
while i > -1:
if i == 1:
category_url = "https://www.safe.gov.cn/safe/zcfgjd/index.html"
else:
category_url = f"https://www.safe.gov.cn/safe/zcfgjd/index_{i}.html"
i = i + 1
max_retries = 5
backoff_factor = 2
retries = max_retries
while retries > 0:
try:
req = urllib.request.urlopen(category_url, timeout=120) # Increased timeout
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list_conr')]/ul/li")
break # Success, exit retry loop
except (urllib.error.URLError, TimeoutError) as error:
logger.error(f"Network error: {error}. Retries left: {retries-1}")
retries -= 1
if retries > 0:
sleep_time = backoff_factor ** (max_retries - retries) + random.uniform(0, 1)
time.sleep(sleep_time)
else:
logger.error(f"Failed to fetch {category_url} after {max_retries} attempts.")
articlelist = []
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//dd/text()")[0]
parsed_datetime = datetime.strptime(
time.strftime("%Y-%m-%d", time.strptime(date, "%Y-%m-%d")),
"%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=delta)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
url = "https://www.safe.gov.cn" + url
article['category'] = "Policy Interpretation"
crawl_by_url(url, article)
except (urllib.error.URLError, etree.XMLSyntaxError) as error:
logger.error(error)
i = 1
while i > -1:
if i == 1:
category_url = "https://www.safe.gov.cn/safe/sjjd/index.html"
else:
category_url = f"https://www.safe.gov.cn/safe/sjjd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(category_url, timeout=60)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list_conr')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//dd/text()")[0]
parsed_datetime = datetime.strptime(
time.strftime("%Y-%m-%d", time.strptime(date, "%Y-%m-%d")),
"%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=delta)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
url = "https://www.safe.gov.cn" + url
article['category'] = "Data Interpretation"
crawl_by_url(url, article)
except (urllib.error.URLError, etree.XMLSyntaxError) as error:
logger.error(error)
|