Created
September 12, 2019 13:54
-
-
Save harrywang/1c9b3b7f9686547327cac77bcf2dd310 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class SaveQuotesPipeline(object): | |
def __init__(self): | |
""" | |
Initializes database connection and sessionmaker | |
Creates tables | |
""" | |
engine = db_connect() | |
create_table(engine) | |
self.Session = sessionmaker(bind=engine) | |
def process_item(self, item, spider): | |
"""Save quotes in the database | |
This method is called for every item pipeline component | |
""" | |
session = self.Session() | |
quote = Quote() | |
author = Author() | |
tag = Tag() | |
author.name = item["author_name"] | |
author.birthday = item["author_birthday"] | |
author.bornlocation = item["author_bornlocation"] | |
author.bio = item["author_bio"] | |
quote.quote_content = item["quote_content"] | |
# check whether the author exists | |
exist_author = session.query(Author).filter_by(name = author.name).first() | |
if exist_author is not None: # the current author exists | |
quote.author = exist_author | |
else: | |
quote.author = author | |
# check whether the current quote has tags or not | |
if "tags" in item: | |
for tag_name in item["tags"]: | |
tag = Tag(name=tag_name) | |
# check whether the current tag already exists in the database | |
exist_tag = session.query(Tag).filter_by(name = tag.name).first() | |
if exist_tag is not None: # the current tag exists | |
tag = exist_tag | |
quote.tags.append(tag) | |
try: | |
session.add(quote) | |
session.commit() | |
except: | |
session.rollback() | |
raise | |
finally: | |
session.close() | |
return item |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment