def process_item_helper(self, item, collection_name):
"""
1. for each post, get rid of 'last_reply_date' key to see if this post has been stored before
2. update/insert the post
"""
adapter = ItemAdapter(item)
post = adapter.asdict()
# get rid of ‘last_reply_date’ key
last_reply_date = ''
if 'last_reply_date' in post:
last_reply_date = post['last_reply_date']
post.pop('last_reply_date')
db_collection = self.db[collection_name]
#logging.debug("search for post: \n %s", post)
# if this post is new, insert the origin post
if db_collection.count_documents(post) == 0:
logging.debug("Insert a new item")
db_collection.insert_one(adapter.asdict())
# this post has been stored before, update
else:
if last_reply_date != '':
logging.debug("Updating an item with last_reply_date %s",
last_reply_date)
db_collection.update_one(
post, {"$set": {
"last_reply_date": last_reply_date
}})
def process_item(self, item, spider):
item = ItemAdapter(item)
if self.is_valid_entry(item):
bisect.insort(self.entries, item['word'])
line = json.dumps(item.asdict(), indent=4, sort_keys=True) + ','
self.file.write(line)
else:
line = json.dumps(item.asdict(), indent=4, sort_keys=True) + ','
self.error_file.write(line)
return item
def process_item(self, item, spider):
item = ItemAdapter(item)
if item['word'] is None:
# if word could not be extracted wirte to errored file
line = json.dumps(item.asdict(), indent=4, sort_keys=True) + ','
self.error_file.write(line)
elif item['definitions'] is None:
# if definition could not be extracted write to errored file
line = json.dumps(item.asdict(), indent=4, sort_keys=True)
self.error_file.write(line)
#else:
# write to database
# write_to_db(self, item.asdict())
return item
def close_spider(self, spider):
res = [ItemAdapter.asdict(item) for item in self.articles]
with open(self.FILENAME, 'w', encoding='utf-8', newline='') as f:
writer = csv.DictWriter(f, fieldnames=list(res[0].keys()))
writer.writeheader()
for i in res:
writer.writerow(i)
def process_item(self, item, spider):
adapter = ItemAdapter(item)
print('In Process Item', adapter.asdict())
if adapter.get('product_price'):
return item
else:
raise DropItem("Missing price in %s" % item)
def process_item(self, item, spider):
adapter = ItemAdapter(item)
# It provides a common interface to extract and set data without having to take the object’s type into account.
if adapter.get('page_num'):
line = "当前页面是第%d页" % item['page_num'] + "\n"
else:
line = json.dumps(adapter.asdict(),
ensure_ascii=False) + "\n" #非ASCII编码，便于人阅读
self.file.write(line)
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
values = adapter.asdict()
empty = lambda field: not field
empty_fields = filter(empty, list(values.values()))
if len(list(empty_fields)) > 12 or values.get("country") != "Kenya":
print("\n\n***************")
print("Dropped")
print("******************\n\n")
raise DropItem("Too many empty values found.")
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
try:
adapter["brand"] = self.clean_text(adapter.get("brand"))
adapter["name"] = self.clean_text(adapter.get("name"))
adapter["price"] = int(
float(adapter.get("price").replace(",", "").split()[1]))
adapter["image"] = adapter.get("image").split("?")[0]
except Exception:
DropItem(f"Missing essential properties in {item}")
self.csv.writerow(adapter.asdict())
return item
def close_spider(self, spider):
if self.items is not []:
for item in self.items:
adapter = ItemAdapter(item)
columns = adapter.field_names()
writer = csv.DictWriter(self.file,
fieldnames=columns,
restval='',
extrasaction='ignore',
delimiter=',',
quoting=csv.QUOTE_NONNUMERIC,
quotechar="\"")
if self.file.tell() == 0:
writer.writeheader()
writer.writerow(adapter.asdict())
self.file.close()
def process_item(self, item, spider):
# Only handle TopicItems
if not isinstance(item, BaseTopicItem):
return item
adapter = ItemAdapter(item)
topic_id = adapter.get('topic_id')
self.logger.debug(f'exporting TopicItem (id: {topic_id})')
path = prepare_path(base_dir=self.base_dir_path,
dirname_template=self.dirname_tmplt,
filename_template=self.filename_tmplt,
item=item)
with path.open('w') as wh:
json.dump(adapter.asdict(), wh)
self.logger.debug(f'exported TopicItem (id: {topic_id})')
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if 'name' in adapter.keys() and 'price' in adapter.keys():
adapter['name'] = [unidecode(adapter['name'][0])]
adapter['price'] = [unidecode(adapter['price'][0])]
str_price = adapter['price'][0]
str_price = str_price.replace('.', '')
str_price = str_price.replace(',', '.')
price = float(str_price)
if 'cents' in adapter.keys():
cents = adapter['cents'][0]
cents = float(cents)
price = price + cents / 100
adapter['price'] = price
self.col.insert_one(adapter.asdict())
print("Exporter:", adapter["name"], "| ", adapter["price"], "|",
adapter['store'])
else:
raise DropItem(f"{item} without name or price")
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
line = json.dumps(adapter.asdict(), ensure_ascii=False) + "\n"
self.file.write(line)
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
line = json.dumps(adapter.asdict(), ensure_ascii=True) + '\n'
self.file.write(line)
print('Item Scraped!')
return item
def process_item(self, item, spider):
adapter = ItemAdapter(item)
adapter['created_at'] = datetime.now().timestamp()
self.items.append(adapter.asdict())
self.db[f'kw-{spider.keyword}'].insert_one(adapter.asdict())
return f"成功抓取关键词 [ {spider.keyword} ] 下的产品 {item['pid']} "
def process_item(self, item, spider):
adapter = ItemAdapter(item)
self.db[self.collection_name].update_one({'url': adapter.get('url')},
{'$set': adapter.asdict()},
upsert=True)
return item
